© 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. 42820
    Prev
    Next
    INDEX
    Explanations

    Foreign text

    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
     meta
    -0.30
    åħĥ
    -0.29
    (meta
    -0.29
    ena
    -0.28
    rarian
    -0.26
    osterone
    -0.26
    inished
    -0.26
    ENA
    -0.26
    åĨħåľ¨
    -0.25
    æ½®
    -0.25
    POSITIVE LOGITS
    ç²¾ç¥ŀ
    0.32
     spirit
    0.29
    æ³ł
    0.27
    иÑĢ
    0.27
     spirits
    0.26
    è¾Ł
    0.26
    zÄħ
    0.24
     Bourbon
    0.24
     Bez
    0.24
    æĺŃ
    0.24
    Activations Density 0.001%

    No Known Activations