© 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. 37662
    Prev
    Next
    INDEX
    Explanations

    first

    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
    ãģĤãĤĮ
    -0.09
    æĺ¨
    -0.09
    è²Įä¼¼
    -0.09
    åªĴä½ĵæĬ¥éģĵ
    -0.09
    æĪ¾
    -0.08
    æĸ°éĹ»åıijå¸ĥ
    -0.08
    иÑĩеÑģк
    -0.08
    icare
    -0.08
     Pratt
    -0.08
     그리
    -0.08
    POSITIVE LOGITS
    å½ĵå¹´
    0.10
    .old
    0.10
    çŃļ
    0.09
    OLDER
    0.09
    èĢģæŧ
    0.09
    istorical
    0.09
     ëĭ¹ìĭľ
    0.09
    å½ĵæŶ
    0.09
    åľ¨è¿ĻéĩĮ
    0.08
    è¿ĺèĥ½
    0.08
    Activations Density 0.070%

    No Known Activations