© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 41181
    Prev
    Next
    INDEX
    Explanations

    loc

    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
    es
    -0.30
    -es
    -0.29
    (es
    -0.28
    hes
    -0.28
    lds
    -0.27
    lore
    -0.26
    nds
    -0.25
    np
    -0.25
    esan
    -0.25
     foremost
    -0.24
    POSITIVE LOGITS
    order
    0.29
     order
    0.28
    Order
    0.26
    гон
    0.26
     Govern
    0.25
    Fed
    0.25
    éĵ¶æ²³
    0.25
    èŁ¹
    0.25
    leta
    0.24
    GO
    0.24
    Activations Density 0.002%

    No Known Activations