© 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. 34942
    Prev
    Next
    INDEX
    Explanations

    Formula related phrases

    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
    гал
    -0.10
    ilton
    -0.09
    aways
    -0.09
     بص
    -0.09
    沫
    -0.08
    æľªæĪIJ
    -0.08
    wright
    -0.08
    parm
    -0.08
    æľ¬æľĪ
    -0.08
    -thirds
    -0.08
    POSITIVE LOGITS
    æĻ°
    0.10
    æªĢ
    0.10
    ing
    0.10
    esor
    0.09
    éĥ½åĸľæ¬¢
    0.09
    s
    0.09
    matic
    0.09
    sed
    0.09
    ity
    0.09
    acin
    0.09
    Activations Density 0.017%

    No Known Activations