© 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. 30390
    Prev
    Next
    INDEX
    Explanations

    vs

    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
    èĩªæķij
    -0.10
    å®Ī
    -0.08
    zac
    -0.08
    两大
    -0.08
    iddles
    -0.08
    elize
    -0.08
    VISION
    -0.08
    ailable
    -0.08
    çĵľ
    -0.08
    uale
    -0.08
    POSITIVE LOGITS
    èģĶç³»æĪij们
    0.13
    æĪijéĻ¢
    0.13
    åķĨçĶ¨
    0.10
    éĹ®æĪij
    0.09
    éĢģæĿ¥
    0.09
     ìłĢíĿ¬
    0.09
    ä¾
    0.09
    æ¯ĶæĪij
    0.09
    æĸ°å½¢åĬ¿
    0.09
    对æĪij们
    0.09
    Activations Density 0.462%

    No Known Activations