© 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. 25-TRANSCODER-HP
    7. 108295
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anje
    -0.26
    ãĥ¼ãĥĹ
    -0.26
    åºĬä½į
    -0.26
     hiá»ĩp
    -0.25
    isque
    -0.24
    sdk
    -0.24
    é£İåIJ¹
    -0.23
    opa
    -0.23
    eq
    -0.23
    æľīç§į
    -0.23
    POSITIVE LOGITS
    æĿĥ
    0.29
    è¡£
    0.27
    --[
    0.27
    nom
    0.26
    ç»ĨèĬĤ
    0.26
    partment
    0.25
     Greek
    0.25
    uding
    0.25
    yling
    0.25
    ston
    0.25
    Activations Density 1.479%

    No Known Activations

    This feature has no known activations.