© 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. 27-TRANSCODER-HP
    7. 56784
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .adjust
    -0.25
    棵æłij
    -0.25
    礼æĭľ
    -0.25
     NodeList
    -0.24
    BuildContext
    -0.24
    rame
    -0.23
    Å¡ÃŃ
    -0.23
    opensource
    -0.23
     manus
    -0.23
    å·´å·´
    -0.23
    POSITIVE LOGITS
     an
    0.29
     Orient
    0.28
    /=
    0.27
    缸åħ³ä¿¡æģ¯
    0.27
    ä¸Ģ个
    0.27
    sworth
    0.26
    ãĥĬãĥ¼
    0.26
    зоÑĢ
    0.25
    è¿Ļåıª
    0.25
    Operation
    0.25
    Activations Density 0.008%

    No Known Activations