© 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. 22933
    Prev
    Next
    INDEX
    Explanations

    size and shape descriptors

    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
    æİ¥çĿĢ
    -0.08
    åĿij
    -0.08
    æ¢ĵ
    -0.08
     calling
    -0.08
    boa
    -0.08
    ä¸ĩ象
    -0.08
    ãģĸ
    -0.08
    稳
    -0.08
    çĽ¸ä¼ł
    -0.08
    èĶĹ
    -0.08
    POSITIVE LOGITS
    å¯Įæľī
    0.11
    ç¼¢
    0.10
    触åıĬ
    0.09
    åĪºå®¢
    0.09
    æĬ¢åħĪ
    0.08
    失æݧ
    0.08
     Kush
    0.08
    ç¥ĸçĪ¶
    0.08
    åıĭ好
    0.08
    èµ·åĪĿ
    0.08
    Activations Density 0.059%

    No Known Activations