© 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. 49841
    Prev
    Next
    INDEX
    Explanations

    cybercrime and criminal activity

    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
    åı¤ä»Ĭ
    -0.09
     enr
    -0.08
    mah
    -0.08
    秣
    -0.08
    nip
    -0.08
    olith
    -0.08
    çļĦä¼ĺåĬ¿
    -0.08
     SE
    -0.08
    åĬ¨
    -0.08
    ORA
    -0.08
    POSITIVE LOGITS
    igers
    0.10
    wins
    0.09
    idl
    0.09
    èĤ®
    0.09
    ToWorld
    0.09
     bÄĥng
    0.09
    èĨı
    0.09
    ä¸ĸçķĮåIJĦåĽ½
    0.09
    çļĩåŃIJ
    0.09
    aptors
    0.09
    Activations Density 0.041%

    No Known Activations