© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26094
    Prev
    Next
    INDEX
    Explanations

    likely to be

    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
    Negative Logits
    æĪijä¸Ģ缴
    -0.10
    岸
    -0.09
    éļ¾éģĵ
    -0.09
    çķĻä½ı
    -0.09
    çĺ¾
    -0.08
    èij«èĬ¦
    -0.08
    æ··ä¹±
    -0.08
    çļĦ羣å®ŀ
    -0.08
    ä½ķåĨµ
    -0.08
    æĽ³
    -0.08
    POSITIVE LOGITS
    osos
    0.10
    rame
    0.09
     ÑģÑĢазÑĥ
    0.09
    forth
    0.08
    amina
    0.08
    æįħ
    0.08
    æŶéĹ´åĴĮ
    0.08
    edList
    0.08
    amo
    0.08
    ìłĢ
    0.08
    Activations Density 0.195%

    No Known Activations