© 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. 50961
    Prev
    Next
    INDEX
    Explanations

    remain

    np_max-act · gemini-2.0-flash
    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
    zc
    -0.08
    [::-
    -0.08
    xis
    -0.07
    _usr
    -0.07
    漉
    -0.07
    抽奖
    -0.07
    🥓
    -0.07
    🐧
    -0.07
     breathed
    -0.07
    双脚
    -0.07
    POSITIVE LOGITS
     remained
    0.09
    ていた
    0.07
     remain
    0.07
     ordinary
    0.07
     energy
    0.07
     hükü
    0.07
     étaient
    0.07
     remaining
    0.06
    텦
    0.06
    ていない
    0.06
    Activations Density 0.028%

    No Known Activations