© 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. 43467
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    iswa
    -0.27
    æijĨ
    -0.27
     tongue
    -0.25
    _choices
    -0.24
    _ins
    -0.24
    andbox
    -0.24
    (phase
    -0.24
    åĬĿ
    -0.24
    geb
    -0.23
    åĹĶ
    -0.23
    POSITIVE LOGITS
    clip
    0.27
     hap
    0.25
    hap
    0.25
    è°ĥæŁ¥
    0.25
    ãģĬãģĭ
    0.25
    conde
    0.24
    /WebAPI
    0.24
    ycin
    0.24
    .flip
    0.24
     Po
    0.23
    Activations Density 0.000%

    No Known Activations