© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 70800
    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
     Philosophy
    -0.07
    特别声明
    -0.06
     todav
    -0.06
     geopol
    -0.06
     Gathering
    -0.06
    plet
    -0.06
    𫠆
    -0.06
    ichick
    -0.06
    Ὅ
    -0.06
     stdClass
    -0.06
    POSITIVE LOGITS
    面积约
    0.08
    (pro
    0.08
    FLOW
    0.08
    bones
    0.07
     diarr
    0.07
     />);↵
    0.07
    ONS
    0.07
    루
    0.07
    ROUTE
    0.07
    _BUCKET
    0.07
    Activations Density 0.018%

    No Known Activations