© 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. 35469
    Prev
    Next
    INDEX
    Explanations

    happy state

    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
    aget
    -0.10
    æµħ
    -0.09
    çľ¼éķľ
    -0.09
    å¹²éĥ¨
    -0.08
    ability
    -0.08
    med
    -0.08
    æĪijè§īå¾Ĺ
    -0.08
    é«ĺ空
    -0.08
    åħħ满
    -0.08
     dá»ĭ
    -0.08
    POSITIVE LOGITS
     camper
    0.10
    ä¸İåIJ¦
    0.10
     enough
    0.10
    TAIL
    0.09
    æ´ĭæ´ĭ
    0.09
    æĹıèĩªæ²»åİ¿
    0.09
    åľ°è¯´
    0.09
    reds
    0.09
    rum
    0.09
    licated
    0.09
    Activations Density 0.010%

    No Known Activations