© 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. 41549
    Prev
    Next
    INDEX
    Explanations

    Code licenses and copyright

    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
    ieties
    -0.28
    潮湿
    -0.27
    sizes
    -0.26
     churches
    -0.25
    ponents
    -0.25
    éĴº
    -0.25
     statuses
    -0.25
     sites
    -0.25
    frames
    -0.25
     flows
    -0.24
    POSITIVE LOGITS
    足
    0.27
    åĬŁèĥ½
    0.26
    å¹³æĿ¿
    0.26
    Arena
    0.25
    æµħ
    0.24
    åħĭ
    0.24
    深度
    0.24
    åħ¨éĿ¢èIJ½å®ŀ
    0.24
    Jon
    0.24
    å¯Ħ
    0.24
    Activations Density 0.001%

    No Known Activations