© 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. 42230
    Prev
    Next
    INDEX
    Explanations

    places and attractions

    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
    责任
    -0.29
     HOLDER
    -0.28
    仪
    -0.26
    å®ļ
    -0.26
    æĴĩ
    -0.25
    stick
    -0.24
    owler
    -0.24
     Wheels
    -0.24
    .getRight
    -0.24
    责任åĪ¶
    -0.24
    POSITIVE LOGITS
     site
    0.31
     shop
    0.27
     tour
    0.27
    osite
    0.26
     museum
    0.26
     TD
    0.26
     Congress
    0.25
    å°±æĺ¯åľ¨
    0.25
     route
    0.25
     house
    0.25
    Activations Density 0.004%

    No Known Activations