© 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. 64456
    Prev
    Next
    INDEX
    Explanations

    filler words

    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
    rgan
    -0.27
    inals
    -0.27
    ohan
    -0.27
     anonym
    -0.26
    icans
    -0.25
    оÑĢдин
    -0.25
    ụ
    -0.25
    raph
    -0.24
    Ñģад
    -0.24
    åķıãģĦ
    -0.24
    POSITIVE LOGITS
    è¢ĭ
    0.29
    æļĤæŶ
    0.28
    -temp
    0.25
    åıijå±ķçļĦ
    0.25
    oley
    0.25
    temp
    0.25
     Temp
    0.25
    溢价
    0.24
    åıijå±ķä¸Ń
    0.24
    ***↵↵
    0.24
    Activations Density 13.811%

    No Known Activations