© 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. 63002
    Prev
    Next
    INDEX
    Explanations

    Viewing or accessing

    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
    就没æľī
    -0.30
    stä
    -0.27
    ious
    -0.27
     ìķĦë§Ī
    -0.27
    ä½łèĩªå·±
    -0.27
    unner
    -0.26
    ä¸į容æĺĵ
    -0.25
    .xticks
    -0.25
    Collider
    -0.25
    setter
    -0.24
    POSITIVE LOGITS
     UserService
    0.27
    ULA
    0.26
     PIN
    0.25
    ÐŀС
    0.25
    çļĦ人
    0.24
    k
    0.24
    agn
    0.24
    éĢĨè¢Ń
    0.24
     Pin
    0.24
    Pin
    0.24
    Activations Density 3.131%

    No Known Activations