© 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 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. 78622
    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
     lớ
    -0.08
    亩
    -0.07
    𐌽
    -0.07
     vom
    -0.07
    .annot
    -0.07
     newVal
    -0.06
    裘
    -0.06
     새
    -0.06
     coffee
    -0.06
    <|im_start|>
    -0.06
    POSITIVE LOGITS
    (cl
    0.07
    _kw
    0.07
     curing
    0.07
    矫正
    0.07
    КА
    0.07
    创造力
    0.06
     Glenn
    0.06
    allowed
    0.06
    Besides
    0.06
    (blocks
    0.06
    Activations Density 0.261%

    No Known Activations