© 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. 27-TRANSCODER-HP
    7. 9384
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĭä¸Ģ
    -0.29
    ç¶ĵ
    -0.26
    ç»ı
    -0.25
    roat
    -0.24
    ç»ıçIJĨ
    -0.24
    olynomial
    -0.24
    æĭĨ
    -0.24
    ä¸ŃåŃĺåľ¨çļĦ
    -0.23
    çīĪ
    -0.23
    åªĴ
    -0.22
    POSITIVE LOGITS
    nym
    0.30
    nı
    0.28
    mand
    0.27
     society
    0.25
    rut
    0.25
    群ä½ĵ
    0.24
     theory
    0.24
    æĢ§å¼º
    0.24
    ocache
    0.24
     cultivation
    0.24
    Activations Density 0.032%

    No Known Activations