© 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. 8880
    Prev
    Next
    INDEX
    Explanations

    Medical/coding questions and information

    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
    EntityManager
    -0.28
    女åıĭ
    -0.27
    纪念é¦Ĩ
    -0.27
    çļĦçIJĨ解
    -0.26
    riad
    -0.26
    童年
    -0.26
    女æľĭåıĭ
    -0.25
     politely
    -0.25
     typing
    -0.25
    å¿ĥçIJĨåĴ¨è¯¢
    -0.25
    POSITIVE LOGITS
     INCLUDED
    0.28
    (&:
    0.26
    prites
    0.26
    ighted
    0.26
     Bradley
    0.24
    amu
    0.24
    frica
    0.24
    hips
    0.24
    ford
    0.24
    aines
    0.24
    Activations Density 0.000%

    No Known Activations