© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 9776
    Prev
    Next
    INDEX
    Explanations

    yet still

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    电动汽车
    -0.07
    _socket
    -0.07
    _nm
    -0.07
    𝘾
    -0.07
    лер
    -0.07
    .Next
    -0.06
     Publishers
    -0.06
    不宜
    -0.06
    ]",
    -0.06
    承诺
    -0.06
    POSITIVE LOGITS
     warranties
    0.07
    (shared
    0.06
    örper
    0.06
     школьн
    0.06
    (mu
    0.06
    肉体
    0.06
    ưỡ
    0.06
    éta
    0.06
     henüz
    0.06
    Higher
    0.06
    Activations Density 0.074%

    No Known Activations