© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2133
    Prev
    Next
    INDEX
    Explanations

    genetic responsible genes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ulton
    -0.09
     prox
    -0.09
    eph
    -0.09
     Fallen
    -0.09
     Denise
    -0.08
    oba
    -0.08
    èĤ©
    -0.08
    ixel
    -0.08
    æĬ¥
    -0.08
    eden
    -0.08
    POSITIVE LOGITS
    éģĹä¼ł
    0.11
    èĢģé¼ł
    0.10
    çŃĽæŁ¥
    0.10
    èŃĺ
    0.09
    åŃĺåľ¨äºİ
    0.09
    çłĶ究
    0.09
     responsible
    0.09
     genes
    0.09
    çłĶ究åijĺ
    0.09
    ä½įäºİ
    0.09
    Activations Density 0.812%

    No Known Activations