© 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. 24271
    Prev
    Next
    INDEX
    Explanations

    porting software or hardware

    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
    Negative Logits
    éĺģ
    -0.11
    éĸ£
    -0.10
    ä¸Ģç¬Ķ
    -0.10
    ç¬Ķ
    -0.10
     пÑĥÑĤ
    -0.10
    åľ°æ¯¯
    -0.09
    æĺ¯è°ģ
    -0.09
    éĥ¨ä½į
    -0.09
    èľ¡
    -0.08
     overthrow
    -0.08
    POSITIVE LOGITS
    folios
    0.10
    /port
    0.09
    èĺij
    0.09
    çĿ¹
    0.09
    åĪ°è¿ĻéĩĮ
    0.09
    folio
    0.09
    tings
    0.09
     McKenzie
    0.09
    icio
    0.08
     trụ
    0.08
    Activations Density 0.046%

    No Known Activations