© 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. 37881
    Prev
    Next
    INDEX
    Explanations

    selection 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
    çĪ¹
    -0.09
    æ»ļ
    -0.09
    datap
    -0.09
    éĻĽ
    -0.09
     whole
    -0.08
    åŀĵ
    -0.08
    olv
    -0.08
    atten
    -0.08
    gers
    -0.08
    ä¸Ģ个éĹ®é¢ĺ
    -0.08
    POSITIVE LOGITS
    ilyn
    0.10
    hire
    0.10
    大å°ı
    0.10
    naire
    0.10
    enne
    0.10
    ctor
    0.10
    LECTION
    0.10
    ç¿ķ
    0.09
     должноÑģÑĤ
    0.09
     иÑģпол
    0.09
    Activations Density 0.012%

    No Known Activations