© 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. 63911
    Prev
    Next
    INDEX
    Explanations

    allowed to

    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
    æºŁ
    -0.12
    rail
    -0.10
    aos
    -0.10
    legate
    -0.10
    æĪijå¸ĮæľĽ
    -0.09
     Claw
    -0.09
    _FB
    -0.09
    åı¯èĥ½æĢ§
    -0.09
    acular
    -0.09
    ail
    -0.09
    POSITIVE LOGITS
    ance
    0.11
    ter
    0.10
    åģļçļĦäºĭæĥħ
    0.09
    anter
    0.08
    olle
    0.08
    TERS
    0.08
    èĦļ
    0.08
    çİĽ
    0.08
    ters
    0.08
    åģļçļĦäºĭ
    0.08
    Activations Density 0.012%

    No Known Activations