© 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. 31967
    Prev
    Next
    INDEX
    Explanations

    factory or plant locations

    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
    ç§ijçłĶéĻ¢æīĢ
    -0.09
    opot
    -0.09
    _BITS
    -0.09
     Chin
    -0.09
    é¦ĸéĥ½
    -0.09
    _la
    -0.09
    èģĶ绾
    -0.09
    åĵŃ
    -0.08
    GINE
    -0.08
    uur
    -0.08
    POSITIVE LOGITS
    å·¥åİĤ
    0.09
    庾
    0.09
    工人
    0.09
     facility
    0.09
    设æĸ½
    0.09
    éĻĶ
    0.08
     Blow
    0.08
    æĸ°åĮº
    0.08
    åį·
    0.08
    æĸ°æł¼å±Ģ
    0.08
    Activations Density 0.055%

    No Known Activations