© 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. 34314
    Prev
    Next
    INDEX
    Explanations

    plot, thriller, suspense, novel 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
    ä¸İä¼Ĺ
    -0.11
    åºľ
    -0.11
    骺
    -0.10
    éĢ®
    -0.10
    åĻ¨åħ·
    -0.10
    ç½ļ
    -0.10
    åIJİèĢħ
    -0.09
    çĸ¹
    -0.09
    ç¨ļ
    -0.09
    emet
    -0.09
    POSITIVE LOGITS
    åī§æĥħ
    0.14
    æĥħèĬĤ
    0.13
    å°ı说
    0.12
     thriller
    0.11
    å°ı說
    0.11
     suspense
    0.11
     novels
    0.10
     genres
    0.10
    æ²»å®ī
    0.10
     romance
    0.10
    Activations Density 0.176%

    No Known Activations