© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21877
    Prev
    Next
    INDEX
    Explanations

    Republic, March, Rey, appreciate

    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
    chap
    -0.10
    羣çĪ±
    -0.09
    æ¡Ģ
    -0.09
    æĪĮ
    -0.08
    樽
    -0.08
    è¾ĭ
    -0.08
    Offline
    -0.08
    dh
    -0.08
    èĥģ
    -0.08
    çIJĨ解åĴĮ
    -0.08
    POSITIVE LOGITS
    åį«çĶŁ
    0.10
    å¾ĹçĽĬ
    0.10
    失
    0.10
    å¹²éĥ¨éĺŁä¼į
    0.10
    TTY
    0.09
    okin
    0.09
    ä¼ĺç¾İ
    0.09
    ä¿ı
    0.09
    ä¸įå°ıå¿ĥ
    0.09
    uling
    0.09
    Activations Density 0.001%

    No Known Activations