© 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. 88580
    Prev
    Next
    INDEX
    Explanations

    Narrative passages

    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
    OMIC
    -0.28
    -xs
    -0.27
     wasn
    -0.27
    éļħ
    -0.26
    æłĩåĩĨ
    -0.25
    èĵ¼
    -0.24
     professional
    -0.24
    è§ĦåĪĻ
    -0.24
    è¿ĺ好
    -0.24
     behaved
    -0.24
    POSITIVE LOGITS
    hist
    0.26
     dop
    0.26
    æŶæĬ¥
    0.26
    æŃ¤äºº
    0.25
    åı¤åŁİ
    0.25
     newName
    0.25
    loth
    0.24
     dots
    0.24
    ==="
    0.24
    为æŃ¢
    0.24
    Activations Density 28.819%

    No Known Activations