© 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. 50594
    Prev
    Next
    INDEX
    Explanations

    diary entries

    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
     rad
    -0.07
    cba
    -0.07
    abilidad
    -0.07
    fst
    -0.07
    דם
    -0.06
    ꜥ
    -0.06
     proactive
    -0.06
    괗
    -0.06
    hammad
    -0.06
    comm
    -0.06
    POSITIVE LOGITS
     ±
    0.08
    姿势
    0.08
    Offset
    0.07
    窗户
    0.07
     washing
    0.07
    支部
    0.07
    挂在
    0.07
    /*.
    0.07
     иде
    0.07
    _ICON
    0.06
    Activations Density 0.003%

    No Known Activations