© 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. 107759
    Prev
    Next
    INDEX
    Explanations

    pregnancy and birth texts

    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
     wakes
    -0.26
    eq
    -0.26
    ection
    -0.25
    ç»ĵ
    -0.25
    çµIJ
    -0.24
    ç¹ĩ
    -0.23
    女æĢ§æľĭåıĭ
    -0.23
    een
    -0.23
     Wife
    -0.23
    enville
    -0.23
    POSITIVE LOGITS
     liv
    0.26
    otas
    0.26
    ages
    0.26
    imizer
    0.24
    æĶ¾æīĭ
    0.24
    ugeot
    0.24
    apixel
    0.24
    е
    0.23
    ÑĮе
    0.23
    illard
    0.23
    Activations Density 0.174%

    No Known Activations