© 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. 19-TRANSCODER-HP
    7. 8775
    Prev
    Next
    INDEX
    Explanations

    Scientific names/codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åįĩ
    -0.27
    åĵªä¸Ģ个
    -0.26
     as
    -0.26
     edges
    -0.26
    .zip
    -0.26
    nod
    -0.25
     dön
    -0.25
     nod
    -0.24
    prü
    -0.24
    çĽ¸ä¼´
    -0.24
    POSITIVE LOGITS
    ITH
    0.26
    IDES
    0.25
    ursday
    0.25
    æī£
    0.25
    UTION
    0.25
     ITS
    0.25
    æĪijä¸Ģ缴
    0.24
    anian
    0.23
    éĢļæĬ¥
    0.23
    æ¸Ĭ
    0.23
    Activations Density 0.109%

    No Known Activations