© 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. 11106
    Prev
    Next
    INDEX
    Explanations

    children, youth, obesity, aggression

    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
    èĢĦ
    -0.10
    çĵł
    -0.10
    é£İæĥħ
    -0.09
    ãĥ«ãĥ¼
    -0.09
    åĶ¤éĨĴ
    -0.09
    æľĢéļ¾
    -0.08
    _kb
    -0.08
    å¸Įå°Ķ
    -0.08
    å®Ļ
    -0.08
    _aw
    -0.08
    POSITIVE LOGITS
    åĩī
    0.11
    æļ´åĬĽ
    0.09
    çļĦåİĭåĬĽ
    0.08
    åĿIJ
    0.08
    ä¸įèī¯
    0.08
    殿åłĤ
    0.08
    墩
    0.08
    è§ħ
    0.08
    æ¾Ħ
    0.08
    æĪijçľģ
    0.08
    Activations Density 0.176%

    No Known Activations