© 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. 102770
    Prev
    Next
    INDEX
    Explanations

    for

    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
     saldırı
    -0.08
     choking
    -0.07
    _KEYWORD
    -0.07
    覆盖
    -0.07
     dermat
    -0.07
     J
    -0.07
    _login
    -0.07
    兕
    -0.07
    监督管理
    -0.06
    läss
    -0.06
    POSITIVE LOGITS
    亿元
    0.08
    億元
    0.07
    (pwd
    0.07
    Priv
    0.07
    -Bar
    0.07
     ENTITY
    0.07
     Things
    0.06
    .async
    0.06
    万美元
    0.06
    PMENT
    0.06
    Activations Density 0.003%

    No Known Activations