© 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. 130384
    Prev
    Next
    INDEX
    Explanations

    source

    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
    ason
    -0.26
    çľĭæ¸ħ
    -0.25
    ucket
    -0.25
     gracias
    -0.24
    uckets
    -0.24
     trần
    -0.24
    tf
    -0.23
    achts
    -0.23
    DOM
    -0.23
    actus
    -0.22
    POSITIVE LOGITS
     found
    0.29
    æ¶ĵ
    0.28
    -channel
    0.27
    åľ¨æѤä¹ĭåīį
    0.26
    ä¹Ŀå¹´
    0.26
     constructed
    0.25
    isis
    0.24
     lent
    0.24
     sever
    0.23
    ä¸ĢéĿ¢
    0.23
    Activations Density 17.411%

    No Known Activations