© 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. 4985
    Prev
    Next
    INDEX
    Explanations

    drug detection, cash, marijuana, enforcement

    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
    æģ¯
    -0.09
    æĭ³
    -0.09
    åĤ¬
    -0.08
    復
    -0.08
    å±Ī
    -0.08
    Bang
    -0.08
    пÑĢавлÑı
    -0.08
    çĸĹæ³ķ
    -0.08
    Smarty
    -0.08
    人群
    -0.08
    POSITIVE LOGITS
    åĹħ
    0.10
    没æĶ¶
    0.09
    gle
    0.09
    çĮª
    0.09
    æĭįåįĸ
    0.09
    cour
    0.09
    Cour
    0.09
    artner
    0.09
    hips
    0.09
    éĹ»
    0.09
    Activations Density 0.274%

    No Known Activations