© 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. 7931
    Prev
    Next
    INDEX
    Explanations

    ares

    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
    å¸ĺ
    -0.29
    亿ä¸ĩ
    -0.28
    两åıª
    -0.28
     safest
    -0.27
    _bucket
    -0.26
    ç½IJ
    -0.25
    ê°ij
    -0.25
     Stars
    -0.24
     Sadd
    -0.24
     Tanks
    -0.24
    POSITIVE LOGITS
    zc
    0.28
    ASIC
    0.26
    eling
    0.25
    åīĬ
    0.25
    éķĸ
    0.24
    EFI
    0.23
    æįŁ
    0.23
    owych
    0.23
    ç»ĻäºĪäºĨ
    0.23
    ,exports
    0.23
    Activations Density 0.024%

    No Known Activations