© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 39480
    Prev
    Next
    INDEX
    Explanations

    olo

    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
     highlight
    -0.07
     reminding
    -0.07
     submitted
    -0.07
    ئيس
    -0.07
     безопас
    -0.07
    _baseline
    -0.06
    .MODE
    -0.06
    lication
    -0.06
     mindfulness
    -0.06
    扣
    -0.06
    POSITIVE LOGITS
    ფ
    0.08
    /apis
    0.08
     غزة
    0.08
    売れ
    0.07
    xfe
    0.07
    地段
    0.07
    /build
    0.07
    不得转载
    0.07
    ･･･
    0.07
     Strings
    0.07
    Activations Density 0.001%

    No Known Activations