© 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. 43392
    Prev
    Next
    INDEX
    Explanations

    Computing and web context

    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
     storage
    -0.31
    -storage
    -0.29
     Storage
    -0.28
    åĤ¨
    -0.28
    _storage
    -0.27
     a
    -0.27
    åľ¨ä¸Ģ个
    -0.27
    storage
    -0.26
     service
    -0.26
    pot
    -0.25
    POSITIVE LOGITS
    distributed
    0.36
     distributed
    0.36
     Distributed
    0.31
    åĪĨæķ£
    0.29
    adel
    0.28
    ë°°
    0.28
    å¾·å°Ķ
    0.28
     dispersed
    0.27
    egr
    0.27
    åĪĨå¸ĥå¼ı
    0.26
    Activations Density 0.001%

    No Known Activations