© 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. 62442
    Prev
    Next
    INDEX
    Explanations

    fiction stories and genres

    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
    itude
    -0.10
    ses
    -0.09
    å¯Įè´µ
    -0.09
    MISS
    -0.09
     tù
    -0.08
    civil
    -0.08
    idue
    -0.08
    _MT
    -0.08
    å¼ĤæĢ§
    -0.08
    htable
    -0.08
    POSITIVE LOGITS
    èµ°å»Ĭ
    0.09
    æ°¤
    0.09
    çĭ¡
    0.08
    çīĸ
    0.08
    unsch
    0.08
    hip
    0.08
    æį¢æĪIJ
    0.08
    èģĶ社
    0.08
    éĤª
    0.08
    annis
    0.08
    Activations Density 0.011%

    No Known Activations