© 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. 32102
    Prev
    Next
    INDEX
    Explanations

    even though

    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
    æŀģåħ·
    -0.09
    å¾Ģå¾Ģæĺ¯
    -0.08
    ãĤ»ãĥĥãĥĪ
    -0.08
    éĶµ
    -0.08
    èµ·çłģ
    -0.08
    æ´¥
    -0.08
    èĭ¥å¹²
    -0.08
    pane
    -0.08
    neau
    -0.08
    ä¸Ī
    -0.08
    POSITIVE LOGITS
    å½¼
    0.12
    è¿Ļå°±
    0.10
     Loud
    0.10
     ÑĤогда
    0.09
    ForRow
    0.09
    è¿Ļ对
    0.09
    éĤ£ä¸ªæŶåĢĻ
    0.09
    åıĹå½±åĵį
    0.09
    ULAR
    0.09
    ÑĢаÐ
    0.09
    Activations Density 0.020%

    No Known Activations