© 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. 31-TRANSCODER-HP
    7. 19034
    Prev
    Next
    INDEX
    Explanations

    just

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     immediately
    -0.41
     immediate
    -0.37
    ç«ĭåį³
    -0.35
     Immediately
    -0.33
     immedi
    -0.30
     ÑģÑĢазÑĥ
    -0.29
    mediately
    -0.28
    füg
    -0.28
     instantly
    -0.28
    Immediately
    -0.28
    POSITIVE LOGITS
    çŁŃ
    0.31
    _past
    0.31
     short
    0.27
    NESS
    0.27
    åĢ¡è®®
    0.27
    ç¬Ķè®°
    0.27
    ä¸ĩ家
    0.27
    past
    0.26
    壬
    0.26
    å¸Ń
    0.26
    Activations Density 0.061%

    No Known Activations