© 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. 20-TRANSCODER-HP
    7. 63603
    Prev
    Next
    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĢ«
    -0.28
    older
    -0.28
    udo
    -0.26
    修身
    -0.25
     Hud
    -0.25
    /mit
    -0.24
    iteral
    -0.24
    IU
    -0.24
    æľºåħ³
    -0.24
    oured
    -0.23
    POSITIVE LOGITS
    è£Ķ
    0.29
    åıįæŃ£
    0.28
    æ±
    0.27
    èĻŀ
    0.26
     DataContext
    0.26
    èĭŁ
    0.26
    _CTX
    0.25
    ðŁĵIJ
    0.25
    toast
    0.24
     applicationContext
    0.24
    Activations Density 16.704%

    No Known Activations