© 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. 57530
    Prev
    Next
    INDEX
    Explanations

    own

    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
    å¤Ķ
    -0.09
    说èĩªå·±
    -0.09
    è¨ĢãģĪãģ°
    -0.09
    bian
    -0.09
    亡
    -0.08
    aison
    -0.08
    çŃ¾è¯ģ
    -0.08
    æĪijè¿ĺ
    -0.08
    ä½łå¥½
    -0.08
     Blink
    -0.08
    POSITIVE LOGITS
    æĴ¬
    0.10
     sno
    0.09
    åľ¨éĩĮéĿ¢
    0.09
    å®ĺæĸ¹ç½ijç«Ļ
    0.08
    abbrev
    0.08
    ä¸Ńæŀ¢
    0.08
    æŶåĪ»
    0.08
    æīĵåĬ¨
    0.08
    oun
    0.08
    åħ´è¶£
    0.08
    Activations Density 0.011%

    No Known Activations