© 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. 63784
    Prev
    Next
    INDEX
    Explanations

    special education disorders

    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
    æį»
    -0.10
    ç©¿çĿĢ
    -0.09
    æģģ
    -0.08
    è§Ħ
    -0.08
    æ±´
    -0.08
    itsu
    -0.08
     Gos
    -0.08
     жиз
    -0.08
    ivre
    -0.08
     trunk
    -0.08
    POSITIVE LOGITS
    ano
    0.09
    ç±³å°Ķ
    0.09
    èŀįåIJĪåıijå±ķ
    0.09
    èĮ¶åĽŃ
    0.09
     remed
    0.08
    олÑı
    0.08
    NAL
    0.08
     mainstream
    0.08
    èŀį
    0.08
    åħīéĺ´
    0.08
    Activations Density 0.054%

    No Known Activations