© 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. 141965
    Prev
    Next
    INDEX
    Explanations

    technical/scientific topics

    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
    GRES
    -0.26
     fwrite
    -0.26
     Anthrop
    -0.25
    ActionResult
    -0.25
     anthrop
    -0.25
    .ping
    -0.25
    oux
    -0.25
    ajo
    -0.25
     sanctioned
    -0.23
    æł¼å°Ķ
    -0.23
    POSITIVE LOGITS
    ilik
    0.26
    å¸
    0.26
    æĩĤäºĭ
    0.26
    iaux
    0.26
    æŶæŶ
    0.25
    rops
    0.25
    едÑĮ
    0.25
     euler
    0.24
    ewise
    0.24
    éĢıè§Ĩ
    0.24
    Activations Density 10.309%

    No Known Activations