© 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. 60893
    Prev
    Next
    INDEX
    Explanations

    cattle and cows

    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
    çIJĨå·¥
    -0.11
     Fir
    -0.11
    æ¿ij
    -0.10
    annel
    -0.09
    åĢĻ
    -0.09
    è¢ĭ
    -0.08
     ÐŀÑĩ
    -0.08
    æ°ijèIJ¥
    -0.08
    __$
    -0.08
    ä¸įå½±åĵį
    -0.08
    POSITIVE LOGITS
    çĬĬ
    0.13
    çīĽ
    0.12
     cows
    0.11
     Cow
    0.11
    èĢķ
    0.10
     cow
    0.10
    èĢķåľ°
    0.09
    åłª
    0.09
    çī
    0.09
    ptime
    0.09
    Activations Density 0.039%

    No Known Activations