© 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. 89539
    Prev
    Next
    INDEX
    Explanations

    Common filler words in text

    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
    èĢĮè¨Ģ
    -0.28
    rome
    -0.28
     manifestation
    -0.27
     amen
    -0.26
     manifest
    -0.26
    ç¦ıéŁ³
    -0.26
     bene
    -0.25
    çĶ¥
    -0.25
    rom
    -0.25
     Cart
    -0.25
    POSITIVE LOGITS
    éĻ¢åī¯éĻ¢éķ¿
    0.28
    ä»£æĽ¿
    0.26
     Videos
    0.26
    åı£æ°´
    0.26
    Warn
    0.25
    acional
    0.25
     viá»ĩn
    0.25
    åĢ«
    0.24
    eut
    0.24
    æĸ¯å¡Ķ
    0.24
    Activations Density 25.328%

    No Known Activations