© 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. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 42715
    Prev
    Next
    INDEX
    Explanations

    eliminating

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sus
    -0.30
    窦
    -0.28
    äºĴ
    -0.28
     lá»ĩ
    -0.28
    ç¥Ī祷
    -0.28
    éĻĨ
    -0.27
     rate
    -0.27
     sus
    -0.26
    ients
    -0.26
    land
    -0.26
    POSITIVE LOGITS
     eliminates
    0.32
     eliminate
    0.31
     eliminated
    0.31
     Elim
    0.31
    Elim
    0.31
    æ¶ĪçģŃ
    0.30
    elim
    0.30
     eliminating
    0.29
    æĪĺèĥľ
    0.29
     controlling
    0.28
    Activations Density 0.001%

    No Known Activations