© 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. 7008
    Prev
    Next
    INDEX
    Explanations

    shooting sports

    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
    ç¥Ŀ
    -0.10
    ammen
    -0.09
    éľľ
    -0.09
    ä¾Ī
    -0.08
     bef
    -0.08
    edin
    -0.08
    éħ¿
    -0.08
    æĭĽ
    -0.08
     Lionel
    -0.08
    _AM
    -0.08
    POSITIVE LOGITS
    éĻIJæŶ
    0.10
    æĽ´é«ĺ
    0.10
    åľºä¸Ĭ
    0.09
    ked
    0.09
    åħ¥åľº
    0.09
    ç»Ī
    0.09
    пиÑĤ
    0.09
    åľº
    0.08
    acr
    0.08
     Beef
    0.08
    Activations Density 0.097%

    No Known Activations