© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52992
    Prev
    Next
    INDEX
    Explanations

    shooting and firearms

    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
    æµĥ
    -0.09
     COLL
    -0.09
    带头
    -0.09
    olg
    -0.08
    åŁĭ
    -0.08
    éªĤ
    -0.08
    åĽĽæĸ¹
    -0.08
    utschen
    -0.08
    wig
    -0.08
    çļĭ
    -0.08
    POSITIVE LOGITS
    èĮķ
    0.10
    åIJ¬çĿĢ
    0.09
    äºĮèĢħ
    0.09
    è¥Ł
    0.09
     tops
    0.09
     Ná»Ļi
    0.09
    erable
    0.09
    第äºĮæī¹
    0.09
    åIJĪæł¼
    0.09
    éĢģåİ»
    0.09
    Activations Density 0.066%

    No Known Activations