© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6033
    Prev
    Next
    INDEX
    Explanations

    process completion

    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
    åį°è±¡æ·±åĪ»
    -0.09
    èĤ¥
    -0.09
    éº»æľ¨
    -0.08
    ÑģÑĤи
    -0.08
    .cls
    -0.08
    erce
    -0.08
    湿
    -0.08
    人æīį
    -0.08
    åİĮ
    -0.08
    åıĹå½±åĵį
    -0.08
    POSITIVE LOGITS
    åħ¶å®ĥéĹ®é¢ĺ
    0.10
    åĩ°
    0.10
    ä¸Ģå±Ĥ
    0.09
    OUCH
    0.09
    çķ¥å¾®
    0.09
    ivol
    0.09
    çķ¥æľī
    0.09
    åįģåĪĨéĴŁ
    0.09
    äºĨäºĽ
    0.09
    宵
    0.09
    Activations Density 0.020%

    No Known Activations