© 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. 49951
    Prev
    Next
    INDEX
    Explanations

    DNA lesion repair

    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
    ä¾ĭå¤ĸ
    -0.10
    éŁ³åĵį
    -0.10
    å¸ĥå°Ķ
    -0.09
    åĬĽäºī
    -0.09
    annis
    -0.09
    å·§
    -0.09
    _Exception
    -0.09
     tapered
    -0.09
    ÇIJ
    -0.09
    éķ¦
    -0.09
    POSITIVE LOGITS
    ä¿®å¤į
    0.12
    èī°
    0.10
    ä¿®
    0.10
    æ¡¢
    0.09
    æ£Ģä¿®
    0.09
    ä¿ĿæĬ¤
    0.09
    修补
    0.09
    psc
    0.09
     repair
    0.09
    enterprise
    0.09
    Activations Density 0.638%

    No Known Activations