© 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. 18505
    Prev
    Next
    INDEX
    Explanations

    hackers and hacking groups

    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
    åIJģ
    -0.10
    bred
    -0.10
     facult
    -0.09
    æĸ°ä¸ī
    -0.09
    acement
    -0.09
    orate
    -0.09
    人éĹ´
    -0.09
    utral
    -0.09
    èħĨ
    -0.09
    amina
    -0.09
    POSITIVE LOGITS
    APE
    0.11
    ken
    0.09
    æĹłç¼ĺ
    0.09
    igu
    0.08
    çĦĺ
    0.08
     group
    0.08
    spir
    0.08
     Hut
    0.08
    对ä¸ŃåĽ½
    0.08
     Cham
    0.08
    Activations Density 0.014%

    No Known Activations