© 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. 51345
    Prev
    Next
    INDEX
    Explanations

    national defense

    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
    IDD
    -0.07
    _SLEEP
    -0.07
    ufig
    -0.07
    endir
    -0.07
    irit
    -0.07
    æ³¥åľŁ
    -0.07
    ugin
    -0.07
    çĿ«æ¯Ľ
    -0.07
    åįģ足
    -0.07
    pus
    -0.07
    POSITIVE LOGITS
    _:*
    0.09
    说æĪij
    0.08
    ием
    0.08
    _^(
    0.08
    æīĢæľīæĥħèĬĤ
    0.08
    æĪijä¸įçŁ¥éģĵ
    0.08
    å²IJ
    0.08
    Ñĩе
    0.08
    èķĻ
    0.08
    åĽłåľ°åĪ¶
    0.08
    Activations Density 1.661%

    No Known Activations