© 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. 42388
    Prev
    Next
    INDEX
    Explanations

    Santa Barbara

    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
     con
    -0.29
     intern
    -0.28
    Western
    -0.27
     conf
    -0.26
     test
    -0.26
    èĴĻ
    -0.25
     caches
    -0.25
    intern
    -0.25
    warts
    -0.25
    ali
    -0.25
    POSITIVE LOGITS
    inct
    0.32
    æĺĻ
    0.31
    mps
    0.28
     crest
    0.27
    èĢĮåİ»
    0.27
    eting
    0.25
    ete
    0.24
    ÑĩиÑĤÑĭва
    0.24
    ète
    0.24
    å¸ĥé²ģ
    0.24
    Activations Density 0.001%

    No Known Activations