© 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. 57709
    Prev
    Next
    INDEX
    Explanations

    what happened

    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
    1
    -0.10
    åĪ°åºķæĺ¯
    -0.10
    8
    -0.09
    åĪ°åºķ
    -0.09
    4
    -0.09
    2
    -0.09
     Ves
    -0.09
    究
    -0.09
    6
    -0.09
    究竣æĺ¯
    -0.09
    POSITIVE LOGITS
    亲çĪ±
    0.11
    èħ´
    0.09
    èĮ¬
    0.09
    amus
    0.09
    olan
    0.09
    ç²Ł
    0.09
    èĬ½
    0.09
    éģĺ
    0.09
     amacı
    0.09
    æī¿åıĹ
    0.09
    Activations Density 0.026%

    No Known Activations