© 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. 17593
    Prev
    Next
    INDEX
    Explanations

    firearms and guns

    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
    饱满
    -0.10
    èĢģé¼ł
    -0.09
    ç»ī
    -0.09
    æĢĤ
    -0.09
    asic
    -0.09
    庶
    -0.09
    ä¸įä»ħè¦ģ
    -0.09
    åħ¨å®¶
    -0.09
    aid
    -0.09
    æ¯ı个人éĥ½
    -0.09
    POSITIVE LOGITS
    sWith
    0.10
    undi
    0.09
    çĶ¨åĵģ
    0.09
    coma
    0.09
    éĶĪ
    0.09
    rouch
    0.08
    æĿĪ
    0.08
    uft
    0.08
    dbg
    0.08
    è¿ľæĻ¯
    0.08
    Activations Density 0.014%

    No Known Activations