© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1025
    Prev
    Next
    INDEX
    Explanations

    science fiction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingly
    -0.10
    oman
    -0.09
    åŃIJéĩĮ
    -0.09
    Ñıми
    -0.09
    elin
    -0.09
    羣å¿ĥ
    -0.09
     Glide
    -0.08
    lost
    -0.08
    opo
    -0.08
     Salv
    -0.08
    POSITIVE LOGITS
    -fiction
    0.13
     fiction
    0.13
    çķĮçļĦ
    0.11
     Fiction
    0.10
    /engine
    0.10
    ilde
    0.10
    /math
    0.10
    fiction
    0.10
    çİ°åľ¨å·²ç»ı
    0.09
    çķĮ
    0.09
    Activations Density 0.017%

    No Known Activations