© 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. 4012
    Prev
    Next
    INDEX
    Explanations

    how do i do something

    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
    ä¸įå¾Ĺä¸į
    -0.09
    anium
    -0.09
    assa
    -0.08
    åıªå¾Ĺ
    -0.08
    çĶ¨äºĨ
    -0.08
     forall
    -0.08
    主è¦ģæľī
    -0.08
    æĢ»æĶ¶åħ¥
    -0.08
    æĮº
    -0.08
    çļĦä¸Ģ大
    -0.08
    POSITIVE LOGITS
    çŁ¥éģĵ
    0.10
    çŁ¥éģĵèĩªå·±
    0.10
    åģļåĪ°
    0.09
    ils
    0.09
    åĮºåĪĨ
    0.09
    éĤ£å°±
    0.09
    éĤ£ä¹Īå¤ļ
    0.09
    åĪ»
    0.09
    çľĭå¾ħ
    0.08
    好好
    0.08
    Activations Density 0.065%

    No Known Activations