© 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. 35426
    Prev
    Next
    INDEX
    Explanations

    journey through places and experiences

    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
    åľĪåŃIJ
    -0.10
    æĤ»
    -0.08
    åĿļæĮģ以
    -0.08
    ç±³ç²ī
    -0.08
    ä¹ħäºĨ
    -0.08
    æĪijè¿ĺæĺ¯
    -0.08
    åľĪ
    -0.08
    é»ĺé»ĺåľ°
    -0.08
    EVER
    -0.08
    å°º
    -0.08
    POSITIVE LOGITS
     journey
    0.13
    éģ¨
    0.13
    æĹħç¨ĭ
    0.12
    å¸¦ä½ł
    0.11
    ç©¿è¶Ĭ
    0.11
    æĬ½è±¡
    0.11
    é¢Ĩçķ¥
    0.10
    voy
    0.10
    hare
    0.10
    ç©¿æ¢Ń
    0.10
    Activations Density 0.076%

    No Known Activations