© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7320
    Prev
    Next
    INDEX
    Explanations

    Equals signs / symbols

    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
    GOR
    -0.26
    女
    -0.25
     rz
    -0.25
    çŁ¾
    -0.25
    æķıæĦŁ
    -0.25
    çľ¨çľ¼
    -0.24
    pragma
    -0.24
    桶
    -0.24
    аÑĨиÑİ
    -0.24
    åīįåIJİ
    -0.24
    POSITIVE LOGITS
    æĦı大
    0.31
    æĬ¥å¤į
    0.27
     prec
    0.27
    ilage
    0.27
    æĹłæĦı
    0.26
     cudd
    0.24
    oped
    0.24
    ope
    0.24
    rium
    0.24
     schedules
    0.24
    Activations Density 0.007%

    No Known Activations