© 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. 26292
    Prev
    Next
    INDEX
    Explanations

    to and from

    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
    {:
    -0.09
    åıĮèĦļ
    -0.09
    ä¾Ŀçħ§
    -0.09
    ç¾İèģĶ
    -0.09
     إذ
    -0.09
    adel
    -0.09
    igm
    -0.09
    å®ĥæĺ¯
    -0.09
    itung
    -0.09
    .apple
    -0.09
    POSITIVE LOGITS
    æķ¬
    0.09
    -inner
    0.08
    éĥ½æĺ¯éĿŀ常
    0.08
    éĥ½éĿŀ常
    0.08
    åįł
    0.08
    ç»ĻåŃ©åŃIJ
    0.08
    TING
    0.08
    horn
    0.08
    ory
    0.08
    ori
    0.07
    Activations Density 0.058%

    No Known Activations