© 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. 55948
    Prev
    Next
    INDEX
    Explanations

    eyewear, eyeglass, Eyre

    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
    éĶ¢
    -0.10
    htar
    -0.10
    urs
    -0.09
    REN
    -0.09
    gable
    -0.09
    æĿµ
    -0.09
     khÄĥn
    -0.09
    ÑħваÑĤ
    -0.09
     تعاÙĦÙī
    -0.09
    пÑĢоÑģ
    -0.08
    POSITIVE LOGITS
    ould
    0.10
    ness
    0.10
    ight
    0.10
    ../../../
    0.10
    ãģĵãģ¨ãģ«
    0.09
    rie
    0.09
    odes
    0.09
    å¨ĺ
    0.09
    lah
    0.08
    dings
    0.08
    Activations Density 0.018%

    No Known Activations