© 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. 28012
    Prev
    Next
    INDEX
    Explanations

    local government entities

    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
    plant
    -0.11
    æħij
    -0.09
    å¾Ī好
    -0.09
    çĻ»ä¸Ĭ
    -0.09
    鸳
    -0.09
    ä¸Ĭä¸ĭ
    -0.09
    骡
    -0.09
    åĩºåİĤ
    -0.08
    å¿ĥåĬ¨
    -0.08
    å¾Īæ¼Ĥ亮
    -0.08
    POSITIVE LOGITS
    ä¸Ģç¬Ķ
    0.09
    åĢĻéĢī
    0.09
    OTS
    0.08
    al
    0.08
    亲çĪ±
    0.08
    åľ°æĸ¹
    0.08
    çīĸ
    0.08
    ä¹İ
    0.08
    åīĢ
    0.08
    许
    0.08
    Activations Density 0.108%

    No Known Activations