© 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. 32116
    Prev
    Next
    INDEX
    Explanations

    permission is granted

    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
    æļ´
    -0.12
    åı»
    -0.09
    æļ´é£İ
    -0.09
    ä¼łå¥ĩ
    -0.09
    /testing
    -0.09
    jour
    -0.09
    æŀ«
    -0.09
    kie
    -0.09
    å½ĵæĹ¥
    -0.09
    lut
    -0.08
    POSITIVE LOGITS
    istic
    0.09
    ç¹ģ
    0.09
    æĮ¤åİĭ
    0.08
    atted
    0.08
     дейÑģÑĤвиÑĤелÑĮно
    0.08
    ãģĹãģı
    0.08
    æĥłæ°ij
    0.08
    ARN
    0.08
    ìĦ±ìĿ´
    0.08
    ais
    0.08
    Activations Density 0.002%

    No Known Activations