© 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. 4028
    Prev
    Next
    INDEX
    Explanations

    a bunch of

    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
    ä¸Ģå¼ł
    -0.11
    ä¸Ģ侧
    -0.11
    æĺ¯ä¸Ģéĥ¨
    -0.11
    第ä¸ĢæŃ¥
    -0.10
    ä¸Ģå¤Ħ
    -0.10
    æĺ¯ä¸Ģ座
    -0.10
    æĺ¯ä¸Ģ个
    -0.10
    ä¸Ģ棵
    -0.10
    ä¸Ģæľ¬ä¹¦
    -0.09
    æĺ¯ä¸Ģ款
    -0.09
    POSITIVE LOGITS
    éĿ¢åŃĶ
    0.10
     обÑĢазом
    0.10
    udder
    0.10
    esz
    0.09
    鼶ç¢İ
    0.09
    ä¸İæѤ
    0.09
    ataka
    0.09
    UME
    0.09
    çİij
    0.09
    åIJĪ
    0.09
    Activations Density 0.244%

    No Known Activations