© 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. 39270
    Prev
    Next
    INDEX
    Explanations

    film festival

    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
    èĦĨ
    -0.09
    课åłĤæķĻåѦ
    -0.09
    æ¼Ķä¹ł
    -0.08
    EH
    -0.08
     Ding
    -0.08
    亲çĪ±
    -0.08
     leagues
    -0.08
    logic
    -0.08
    éĢģå¾Ģ
    -0.08
    课åłĤ
    -0.08
    POSITIVE LOGITS
    åīįå¤ķ
    0.14
    æľŁéĹ´
    0.14
    ç»ĵæĿŁåIJİ
    0.12
    æľŁéĸĵ
    0.10
    帷
    0.09
    为å¥ijæľº
    0.09
    缸åħ³ä¿¡æģ¯
    0.09
    ãģ«åĩº
    0.09
    ivals
    0.09
    æ°Ķæ°Ľ
    0.09
    Activations Density 0.138%

    No Known Activations