© 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. 5171
    Prev
    Next
    INDEX
    Explanations

    drum or barrel

    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
    èĪ¸
    -0.10
    æ²Ĩ
    -0.10
    æİĸ
    -0.09
    è¡ĵ
    -0.09
    æĦ¦
    -0.09
    è§īæĤŁ
    -0.09
    æĦł
    -0.09
     Knights
    -0.09
    çĺģ
    -0.09
    ç»°
    -0.09
    POSITIVE LOGITS
    ç«ĭãģ¦
    0.10
    çŃĴ
    0.09
    æ»ļåĬ¨
    0.09
    è¦ģåİ»
    0.08
    alom
    0.08
    æ±ģ
    0.08
    alis
    0.08
    æĪ¿
    0.08
    ç²¾éĢī
    0.08
     Separator
    0.08
    Activations Density 0.037%

    No Known Activations