© 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. 108244
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
    å¥Ĥ
    -0.28
     yourselves
    -0.26
    plx
    -0.24
    æĪĺçķ¥æĢ§
    -0.24
     amplify
    -0.24
    è®ĵä»ĸåĢij
    -0.24
    (thing
    -0.24
    prd
    -0.23
     themselves
    -0.23
     romant
    -0.23
    POSITIVE LOGITS
    æĢ»çļĦ
    0.25
    æĸ°çļĦ
    0.25
    ider
    0.25
     HASH
    0.25
    Extension
    0.25
    çļĦåľ°æŃ¥
    0.24
     extended
    0.24
    led
    0.24
    MOD
    0.24
    [new
    0.24
    Activations Density 15.188%

    No Known Activations