© 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. 49193
    Prev
    Next
    INDEX
    Explanations

    Weird wolf

    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
    ç»ij
    -0.08
    æijĺ
    -0.08
    ç¥ŀ
    -0.08
    opper
    -0.08
    è¡Į人
    -0.08
    积水
    -0.08
    æĶĴ
    -0.08
    涨
    -0.08
    å¤ļå±Ĥ次
    -0.08
    室åĨħ
    -0.08
    POSITIVE LOGITS
    éĥ¨åī¯
    0.10
    æĶ»åĿļæĪĺ
    0.09
    æ±°
    0.09
    åĬŃ
    0.09
    çĶµè§Ĩåı°
    0.09
    еÑĢÑĭ
    0.09
    æ¯Ķäºļ
    0.09
    æģ¨
    0.09
    åıĸèĥľ
    0.09
    éĢĬ
    0.08
    Activations Density 0.065%

    No Known Activations