© 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. 22936
    Prev
    Next
    INDEX
    Explanations

    Star or Motion followed by Ltd or Licensed

    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
    alars
    -0.10
     Dimit
    -0.09
    祺
    -0.09
    propri
    -0.08
    ance
    -0.08
    ly
    -0.08
     Mein
    -0.08
    rais
    -0.08
    endon
    -0.08
    _MEDIUM
    -0.08
    POSITIVE LOGITS
    å½ĵæĪij
    0.10
    adel
    0.09
    ä¸įèĩ³äºİ
    0.09
    审
    0.09
     opposition
    0.08
     ÙħÙĤابÙĦ
    0.08
    intern
    0.08
    ä¸įå¿ĺ
    0.08
    èĥĥåı£
    0.08
     anth
    0.08
    Activations Density 0.004%

    No Known Activations