© 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. 6247
    Prev
    Next
    INDEX
    Explanations

    CakePHP

    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
    ize
    -0.10
    ible
    -0.09
    ized
    -0.09
    OND
    -0.09
    ìĤ¬íķŃ
    -0.09
    IBLE
    -0.09
    æ´®
    -0.08
    å·¥ä½ľä½ľé£İ
    -0.08
    uka
    -0.08
    ised
    -0.08
    POSITIVE LOGITS
    busters
    0.11
    lets
    0.11
    èĤŁ
    0.11
    stry
    0.10
    ERY
    0.10
    let
    0.10
    วย
    0.10
    ÙĦاÙħ
    0.10
    yr
    0.09
    mates
    0.09
    Activations Density 0.010%

    No Known Activations