© 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. 30394
    Prev
    Next
    INDEX
    Explanations

    seeing more

    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
    æijĺ
    -0.12
    RIPT
    -0.10
    åĴ¥
    -0.09
    éķ¿çº¦
    -0.09
    Assignable
    -0.09
    _EV
    -0.09
    ç¾½
    -0.09
    åķģ
    -0.09
    åĪ°æľĢåIJİ
    -0.09
    æĬ½æ£Ģ
    -0.09
    POSITIVE LOGITS
     something
    0.09
    æīĭç»Ń
    0.09
    angan
    0.08
    éĢĤæŶ
    0.08
    æĹĦ
    0.08
    éĵ¢
    0.08
     jednak
    0.08
    èĢĨ
    0.08
    altar
    0.08
    该å¦Ĥä½ķ
    0.08
    Activations Density 0.054%

    No Known Activations