© 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. 58824
    Prev
    Next
    INDEX
    Explanations

    mandate or mandates

    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
    dale
    -0.10
    èĦIJ
    -0.10
    ness
    -0.10
     Buchanan
    -0.10
     Gel
    -0.09
    man
    -0.09
    side
    -0.09
    寻常
    -0.09
    nt
    -0.09
    олÑĮ
    -0.09
    POSITIVE LOGITS
    ìĤ¬íķŃ
    0.11
    geber
    0.10
    pcs
    0.10
    /problem
    0.09
    ×ķר×Ļ
    0.09
    eer
    0.09
    ä¸ĵ人
    0.09
    æīĢæľī人éĥ½
    0.08
    aky
    0.08
     поÑģл
    0.08
    Activations Density 0.007%

    No Known Activations