© 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. 49618
    Prev
    Next
    INDEX
    Explanations

    sports sales decline

    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
    åĩºæĿ¥çļĦ
    -0.11
    è°
    -0.10
    èľī
    -0.10
    æĦı大
    -0.09
    assen
    -0.09
    室
    -0.09
    quit
    -0.09
    éĢłç¦ı
    -0.09
    listing
    -0.09
    MO
    -0.08
    POSITIVE LOGITS
     Russo
    0.10
    odi
    0.09
    å¦ĸ
    0.09
    çĽ¸äº²
    0.08
    äºŃ
    0.08
     Nagar
    0.08
    еÑģÑĮ
    0.08
    æĦį
    0.08
    tech
    0.08
    æ¡IJ
    0.08
    Activations Density 0.016%

    No Known Activations