© 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. 129852
    Prev
    Next
    INDEX
    Explanations

    punctuation/code

    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
    obic
    -0.29
    rek
    -0.27
    å°¤åħ¶
    -0.26
    _rq
    -0.26
    icularly
    -0.25
    WithName
    -0.25
    aries
    -0.25
     universal
    -0.25
    iani
    -0.25
    oner
    -0.24
    POSITIVE LOGITS
    å°ĸ
    0.27
     operated
    0.26
     Today
    0.25
    head
    0.25
    迷人
    0.25
    对å¾ħ
    0.24
    plets
    0.24
    å½ĵä¹ĭ
    0.24
    eslint
    0.24
    respect
    0.24
    Activations Density 21.598%

    No Known Activations