© 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. 63903
    Prev
    Next
    INDEX
    Explanations

    can't verb

    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
    emes
    -0.11
    éĥ½ä¸įæķ¢
    -0.10
    åĪ©çĶ¨çİĩ
    -0.09
    äºĽ
    -0.09
    äºĨäºĽ
    -0.09
    aled
    -0.08
    loid
    -0.08
    åĩĽ
    -0.08
    ä¸Ĭå®ĺ
    -0.08
    è¾Ľ
    -0.08
    POSITIVE LOGITS
    .ContentType
    0.09
    强è¡Į
    0.09
    ä»»ä½ķä¸Ģ个
    0.09
    Öĥ
    0.09
    asma
    0.09
    èĵģ
    0.09
    为导åIJij
    0.08
    ä¸įäºĨ解
    0.08
    èĵł
    0.08
    åħħåĪĨä½ĵçİ°
    0.08
    Activations Density 0.036%

    No Known Activations