© 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. 12-TRANSCODER-HP
    7. 23421
    Prev
    Next
    INDEX
    Explanations

    Act

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istan
    -0.26
    楼主
    -0.26
    .xhtml
    -0.25
    utoff
    -0.25
    овиÑĩ
    -0.25
     INCLUDED
    -0.25
    æĪijåı¯ä»¥
    -0.24
    åħ¼èģĮ
    -0.24
     Compet
    -0.23
    (PyObject
    -0.23
    POSITIVE LOGITS
    é¢ĦçķĻ
    0.28
    SYS
    0.28
     Ire
    0.28
    çķĻ
    0.24
     Ju
    0.24
    <W
    0.24
    Stick
    0.24
    elyn
    0.24
    клон
    0.24
    eline
    0.23
    Activations Density 0.004%

    No Known Activations