© 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. 89111
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific writing

    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
    å½ĵ代
    -0.30
     current
    -0.28
     public
    -0.28
     mock
    -0.28
    åħ¬åħ±
    -0.27
    _mock
    -0.26
    current
    -0.26
    mock
    -0.26
    erie
    -0.26
     PUBLIC
    -0.25
    POSITIVE LOGITS
    LAS
    0.28
    кÑĥп
    0.25
     Lancaster
    0.25
    ä¸Ģæĺ¯
    0.25
    appers
    0.25
     Singles
    0.25
    ä»Ĺ
    0.25
    =cut
    0.25
    acre
    0.25
    iators
    0.25
    Activations Density 52.090%

    No Known Activations