© 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. 8615
    Prev
    Next
    INDEX
    Explanations

    towards

    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
     Nationwide
    -0.29
    ç»Ŀ对
    -0.28
     abroad
    -0.27
     Copies
    -0.27
     ourselves
    -0.27
    GridColumn
    -0.26
    ä¸Ĭå¸Ĥ
    -0.26
    éĢļæĬ¥
    -0.26
    åľ¨åħ¨åĽ½
    -0.26
     copies
    -0.25
    POSITIVE LOGITS
    ä¸į对
    0.27
    åĭĺ
    0.25
    æĤ²è§Ĥ
    0.24
    åģıåIJij
    0.24
    å°±è¿ŀ
    0.24
    æŁĶæĢ§
    0.24
    å¾ĺå¾Ĭ
    0.24
    awi
    0.23
    缸åĬ©
    0.23
    _detect
    0.23
    Activations Density 0.089%

    No Known Activations