© 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. 18-TRANSCODER-HP
    7. 88669
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asion
    -0.30
    !).↵↵
    -0.27
    !).
    -0.26
    edian
    -0.26
    -native
    -0.25
    NullException
    -0.25
    /commons
    -0.25
    adients
    -0.25
    åĶij
    -0.24
    uales
    -0.24
    POSITIVE LOGITS
    itura
    0.26
    åĬłå¿«æİ¨è¿Ľ
    0.25
    çĸ¤
    0.25
    æĩĤå¾Ĺ
    0.24
     ÑĢеж
    0.24
    ä½ĵåĪ¶æĶ¹éĿ©
    0.23
    .separator
    0.23
    oteca
    0.23
    rosso
    0.23
    å¹´ç»Ī
    0.23
    Activations Density 62.294%

    No Known Activations

    This feature has no known activations.