© 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. 57856
    Prev
    Next
    INDEX
    Explanations

    academic and publication terms

    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
    ROUGH
    -0.09
    èĭĭ
    -0.09
    é£İæļ´
    -0.09
    ÑĢог
    -0.09
    ÑĢаÑģÑĤ
    -0.09
    egend
    -0.08
    اØŃ
    -0.08
    æ°®
    -0.08
    æĥ¡
    -0.08
    äº
    -0.08
    POSITIVE LOGITS
    çļĦåħ·ä½ĵ
    0.08
    ç¿Ķ
    0.08
    enze
    0.08
    ä½Ĩå¦Ĥæŀľ
    0.08
    ä¸įæ¸ħæ¥ļ
    0.08
    俱
    0.08
    -paper
    0.07
     kayna
    0.07
    ürü
    0.07
    .synthetic
    0.07
    Activations Density 0.190%

    No Known Activations