© 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. 25-TRANSCODER-HP
    7. 107789
    Prev
    Next
    INDEX
    Explanations

    code contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹Łå¸ĮæľĽ
    -0.30
    ä¹Łä¸įæĥ³
    -0.29
    ÑĪение
    -0.27
    ä¹Łä¸įä¼ļ
    -0.26
    æĤłæĤł
    -0.26
    æģŃæķ¬
    -0.25
    æģ¯
    -0.25
    ãģĹãģ¾
    -0.25
    (TM
    -0.24
    è¿Ļ个åIJįåŃĹ
    -0.24
    POSITIVE LOGITS
    èĴ
    0.30
    elocity
    0.26
    Scope
    0.26
    ÎŃ
    0.25
    .Guid
    0.24
    å¼ģ
    0.24
     scope
    0.24
    ivities
    0.24
    åįĹæŀģ
    0.24
    缴åĪ°
    0.23
    Activations Density 0.076%

    No Known Activations