© 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. 64119
    Prev
    Next
    INDEX
    Explanations

    inbox

    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
    é£İè²Į
    -0.09
    说ä»Ģä¹Ī
    -0.09
    akis
    -0.09
    Implicit
    -0.08
    ities
    -0.08
     Ñģобой
    -0.08
    кÑĢа
    -0.08
    åħĭæĸ¯
    -0.08
    stown
    -0.08
    uct
    -0.08
    POSITIVE LOGITS
    éĩĮçļĦ
    0.11
    æ·±å¤Ħ
    0.11
    è£ı
    0.10
    ActionCode
    0.10
    裡
    0.10
    entifier
    0.10
    otropic
    0.10
    åįłæľīçİĩ
    0.10
    ç¾İèªī
    0.09
    lush
    0.09
    Activations Density 0.014%

    No Known Activations