© 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. 49905
    Prev
    Next
    INDEX
    Explanations

    even

    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
    éĥĬåĮº
    -0.09
    çľī头
    -0.08
    çļĦèĦ¸
    -0.08
    å°±å¤Ł
    -0.08
     increasingly
    -0.08
    åįİå°Ķ
    -0.08
    岸边
    -0.08
    人æ°Ķ
    -0.08
    æ¡ĵ
    -0.08
    _except
    -0.08
    POSITIVE LOGITS
    åĽŀ家
    0.10
    @mail
    0.10
    æ¿ij
    0.09
    è¿Ľä¸ĢæŃ¥
    0.09
    lod
    0.09
    æ¯ı人
    0.09
     деÑıÑĤелÑĮноÑģÑĤÑĮ
    0.09
     pet
    0.09
    æ¦ľ
    0.09
    å°ļ书
    0.09
    Activations Density 0.026%

    No Known Activations