© 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. 30-TRANSCODER-HP
    7. 96652
    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_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĿĢ
    -0.25
     Socket
    -0.25
    isons
    -0.25
    resas
    -0.25
     sayılı
    -0.25
    inx
    -0.24
    /story
    -0.24
     Wall
    -0.24
    å¨ij
    -0.24
    ãģĻãģ¹ãģį
    -0.23
    POSITIVE LOGITS
     Hearts
    0.29
     chim
    0.28
     Kann
    0.27
     vas
    0.27
     rig
    0.26
    ocht
    0.26
    âĭ®
    0.26
     hail
    0.25
    åѤç«ĭ
    0.25
    ccione
    0.25
    Activations Density 0.125%

    No Known Activations