© 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. 8609
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    عÙĬ
    -0.31
     lab
    -0.28
    ä¸ĩ
    -0.25
    åĩºåıij
    -0.25
    åıĮ
    -0.25
    åľĨ
    -0.25
    _lib
    -0.24
    alue
    -0.24
    ©
    -0.24
    _reaction
    -0.24
    POSITIVE LOGITS
    ingleton
    0.29
    æľ¬ç½ij
    0.26
    ipel
    0.25
    åįĬå²Ľ
    0.25
    壮大
    0.25
    below
    0.25
    ç¼
    0.24
     Crescent
    0.24
     princip
    0.24
    íİ´
    0.24
    Activations Density 0.004%

    No Known Activations