© 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. 22557
    Prev
    Next
    INDEX
    Explanations

    providing assistance and help

    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
    .subscribe
    -0.10
    è¿ŀå¤ľ
    -0.10
    åĪºæ¿Ģ
    -0.10
    èĩŃ
    -0.09
    审
    -0.09
    åĪ¶ä½ľ
    -0.09
    éĤ®å¯Ħ
    -0.09
    污水
    -0.09
    å¿ħå¤ĩ
    -0.09
    ahoo
    -0.09
    POSITIVE LOGITS
    示æĦı
    0.13
    æĭĽåij¼
    0.11
    å¼ķ导
    0.11
    çİ°åľº
    0.10
    åħ¨åľº
    0.10
    æī«çłģ
    0.10
    ä¸Ĭåīį
    0.10
    å¿Ļ
    0.09
    æŃ¢
    0.09
    пÑĥÑģ
    0.09
    Activations Density 0.064%

    No Known Activations