© 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. 27306
    Prev
    Next
    INDEX
    Explanations

    don't care if

    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
    éĢĤåIJĪèĩªå·±
    -0.11
    æĹłå½¢
    -0.08
    è£Ĥ
    -0.08
    æĦģ
    -0.08
    åħ¼
    -0.08
     Ñģвое
    -0.08
    èĮ«çĦ¶
    -0.08
    æĬī
    -0.08
     Indo
    -0.08
    çŁ¥å·±
    -0.08
    POSITIVE LOGITS
    åľ°è¯´
    0.11
    wyn
    0.10
    æŧ
    0.10
    åıªè¦ģ
    0.09
    åıªè¦ģä½ł
    0.09
    iane
    0.09
    ffen
    0.09
    ä¼ijåģĩ
    0.09
    /widget
    0.08
    encing
    0.08
    Activations Density 0.009%

    No Known Activations