© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 60036
    Prev
    Next
    INDEX
    Explanations

    mentions of an IT support/technician helping a customer (visiting her home and assisting with computer problems).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VILLE
    -0.08
    푀
    -0.08
     màn
    -0.07
    没事
    -0.07
    蛋
    -0.07
    糗
    -0.07
    Shield
    -0.07
    馌
    -0.07
     عملية
    -0.07
    的衣服
    -0.07
    POSITIVE LOGITS
     ")
    0.07
    >L
    0.07
    _LR
    0.07
    fel
    0.07
    .Res
    0.07
    깍
    0.07
     })();↵
    0.06
     delegation
    0.06
    jr
    0.06
    _minimum
    0.06
    Activations Density 0.083%

    No Known Activations