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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77974
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    حر
    -0.08
     ger
    -0.08
    oure
    -0.07
    (train
    -0.07
     øns
    -0.07
    逢
    -0.07
    经营
    -0.07
    卫生间
    -0.07
    -rise
    -0.07
    ОР
    -0.06
    POSITIVE LOGITS
     ---↵
    0.07
     Neptune
    0.07
    TickCount
    0.07
    نج
    0.07
     окружа
    0.07
    再一次
    0.07
    頂
    0.06
    Multip
    0.06
    ḯ
    0.06
    inine
    0.06
    Activations Density 0.060%

    No Known Activations