© 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. 24347
    Prev
    Next
    INDEX
    Explanations

    playing at spots

    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
    [at
    -0.09
    rans
    -0.09
    å¤Ł
    -0.09
    _SEP
    -0.08
    alie
    -0.08
    ubber
    -0.08
    çĹĽ
    -0.08
    ç»Ń约
    -0.08
    ENSITY
    -0.08
    æĴŃ
    -0.08
    POSITIVE LOGITS
    å¸Ń
    0.11
    éĩįä»»
    0.10
    æĭħè´Ł
    0.10
    è¿ĩ渡
    0.10
    è¾ħ
    0.09
     duties
    0.09
    常æĢģåĮĸ
    0.09
    Ñģад
    0.09
    assi
    0.09
    è¡Į使
    0.09
    Activations Density 0.029%

    No Known Activations