© 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. 107969
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     compliments
    -0.28
    .mousePosition
    -0.25
    UME
    -0.24
     accompanies
    -0.23
    è¨Ģ
    -0.23
    _WAKE
    -0.23
     giveaways
    -0.23
     fame
    -0.23
     wipes
    -0.23
    豨
    -0.23
    POSITIVE LOGITS
    either
    0.32
     either
    0.32
    æĶ¾æĿ¾
    0.30
     Either
    0.28
    Either
    0.27
    çIJĨ
    0.25
     relax
    0.25
    ild
    0.25
    ç¿»
    0.25
    æĿ¾å¼Ľ
    0.24
    Activations Density 1.869%

    No Known Activations