© 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. 89134
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    mmas
    -0.29
     piece
    -0.26
    zenia
    -0.25
     thunk
    -0.25
    outines
    -0.24
    ä¾ĽéĶĢ
    -0.24
    urtles
    -0.24
    ucceeded
    -0.24
    CAPE
    -0.23
    -piece
    -0.23
    POSITIVE LOGITS
     contr
    0.26
    å©Ĩ
    0.26
    oday
    0.25
    ).__
    0.25
    è·Łä»ĸ
    0.25
    oned
    0.25
    è¦ģæ¯Ķ
    0.24
    IX
    0.24
     ranks
    0.24
    è·Łå¥¹
    0.24
    Activations Density 8.788%

    No Known Activations