© 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. 30832
    Prev
    Next
    INDEX
    Explanations

    Oklahoma

    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
    ional
    -0.10
    lessly
    -0.10
    hips
    -0.09
    liest
    -0.09
    æĦıå¢ĥ
    -0.09
    ius
    -0.09
    ä¸Ĭæµ·
    -0.09
    é²Ī
    -0.09
    pulse
    -0.08
    nin
    -0.08
    POSITIVE LOGITS
    èĪĽ
    0.09
    说æĺ¯
    0.09
     Oklahoma
    0.09
    /or
    0.09
    ÑĢÑĥж
    0.09
    éĻĤ
    0.09
    ope
    0.08
    çĸĥ
    0.08
    æݾ
    0.08
    èĵģ
    0.08
    Activations Density 0.007%

    No Known Activations