© 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. 14-TRANSCODER-HP
    7. 40566
    Prev
    Next
    INDEX
    Explanations

    disease

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olith
    -0.34
    cast
    -0.28
    åĶ±
    -0.27
     casts
    -0.27
    åħī彩
    -0.26
    quia
    -0.26
     Narrow
    -0.26
     relative
    -0.26
    æķ²
    -0.26
     Relative
    -0.25
    POSITIVE LOGITS
     Tuấn
    0.28
    è½Ń
    0.25
    _FC
    0.24
    ä¹Łä¸įæĺ¯
    0.24
    èĢģå¸Ī们
    0.24
     EFF
    0.23
    笥
    0.23
    @qq
    0.23
    /down
    0.23
    ä¹Łä¸įæķ¢
    0.23
    Activations Density 0.582%

    No Known Activations