© 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. 7155
    Prev
    Next
    INDEX
    Explanations

    scientific/abstract writing

    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
     presence
    -0.31
    éĿ´
    -0.27
    æķıæĦŁ
    -0.25
    -that
    -0.25
    éĹ¼
    -0.24
    DOT
    -0.24
     cons
    -0.24
    æķıéĶIJ
    -0.23
     налиÑĩие
    -0.23
    _presence
    -0.22
    POSITIVE LOGITS
    ä¸ĢæĿ¡é¾Ļ
    0.29
    ej
    0.27
    å¾Ĺ天
    0.26
    /mit
    0.26
    kte
    0.25
     minded
    0.25
    å²IJ
    0.24
    æĽ¿ä»£
    0.24
    Editors
    0.24
    viron
    0.24
    Activations Density 0.108%

    No Known Activations