© 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. 10862
    Prev
    Next
    INDEX
    Explanations

    directory listings

    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¸į论
    -0.10
    å°Ŀ
    -0.10
    æīĢåľ¨çļĦ
    -0.10
    æīĵåį¡
    -0.09
    ç½Ł
    -0.09
    erset
    -0.09
     Marr
    -0.09
    ubar
    -0.09
    çıł
    -0.08
    泯
    -0.08
    POSITIVE LOGITS
    illions
    0.09
    æ±Ĭ
    0.08
    оÑģÑĤи
    0.08
    第ä¸Ģæī¹
    0.08
     których
    0.08
    uzu
    0.08
    æģ°
    0.08
     Toilet
    0.08
    ç®Ń
    0.08
    каз
    0.07
    Activations Density 0.007%

    No Known Activations