© 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. 5340
    Prev
    Next
    INDEX
    Explanations

    .com / .me / TweetDeck / Flipboard

    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
    éŀł
    -0.09
    /ext
    -0.09
    ban
    -0.09
    ele
    -0.09
    罩
    -0.08
    èĪħ
    -0.08
     Contributor
    -0.08
    ussy
    -0.08
     Ven
    -0.08
    ven
    -0.08
    POSITIVE LOGITS
    ging
    0.10
    éģĩéļ¾
    0.10
    inati
    0.09
    çļĦåİĭåĬĽ
    0.09
    è¶Ĭ
    0.09
    éĨ®
    0.09
    é©°
    0.09
    èģĶ社
    0.09
    å¯Ĥ
    0.09
    äºĨæĪijçļĦ
    0.08
    Activations Density 0.004%

    No Known Activations