© 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. 8163
    Prev
    Next
    INDEX
    Explanations

    technical articles

    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
     Diss
    -0.34
     weighing
    -0.31
    åIJĥ饱
    -0.29
     powder
    -0.28
    ç¢İ
    -0.27
    åĴĢ
    -0.27
     weigh
    -0.27
    åĸĿ
    -0.27
    æĸ¤
    -0.27
    鸡èĽĭ
    -0.25
    POSITIVE LOGITS
    ôn
    0.29
    inus
    0.25
    ernet
    0.25
    metic
    0.25
    nad
    0.25
    åīį沿
    0.24
    landers
    0.24
     quê
    0.24
    render
    0.24
    ptime
    0.24
    Activations Density 0.001%

    No Known Activations