© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5974
    Prev
    Next
    INDEX
    Explanations

    Roku

    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
    åİĿ
    -0.09
    ลà¸Ńย
    -0.08
    agens
    -0.08
    驼
    -0.08
    åľ°ä¸Ń
    -0.08
    inning
    -0.08
    och
    -0.08
    ondon
    -0.08
    è·»
    -0.07
    _EXECUTE
    -0.07
    POSITIVE LOGITS
    å³Ĵ
    0.10
    HOOK
    0.09
    SCP
    0.09
    åĻİ
    0.09
    æĮĤéĴ©
    0.09
     sáng
    0.09
    å·¨æĺŁ
    0.09
    ting
    0.09
    olon
    0.09
    ë£Į
    0.09
    Activations Density 0.004%

    No Known Activations