© 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. 18-TRANSCODER-HP
    7. 89036
    Prev
    Next
    INDEX
    Explanations

    scientific notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    launcher
    -0.30
    ç»°
    -0.25
    DebugEnabled
    -0.24
    ØŃاÙĨ
    -0.24
    quine
    -0.24
    onica
    -0.24
     Frances
    -0.24
    .gt
    -0.24
    åĵ¥
    -0.24
    NewItem
    -0.23
    POSITIVE LOGITS
    å®Įæķ´çļĦ
    0.27
    çķħéĢļ
    0.26
     Py
    0.25
    re
    0.25
    %
    0.25
    èĤ¡
    0.24
    åĬłéĢŁ
    0.24
    æŀĦ
    0.24
    æīĭ段
    0.24
    çŃ
    0.24
    Activations Density 18.535%

    No Known Activations