© 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. 32-TRANSCODER-HP
    7. 42282
    Prev
    Next
    INDEX
    Explanations

    medical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pedest
    -0.27
    æ¹Ľ
    -0.26
    @interface
    -0.26
    Pixel
    -0.24
    esh
    -0.24
    ean
    -0.24
     LAND
    -0.24
    åĨĪ
    -0.24
    .microsoft
    -0.24
    anking
    -0.23
    POSITIVE LOGITS
    åĨħåĪĨæ³Į
    0.26
    åĩij
    0.26
    _dup
    0.26
    èĢĨ
    0.25
    (bottom
    0.25
    Lo
    0.25
    Wa
    0.24
     ds
    0.24
     Lo
    0.24
    [ix
    0.24
    Activations Density 0.005%

    No Known Activations