© 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. 33549
    Prev
    Next
    INDEX
    Explanations

    social dominance and testosterone

    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
    å¿ĥä¸Ń
    -0.09
    AMI
    -0.09
     carnival
    -0.09
    弯
    -0.09
    åĩĭ
    -0.09
    wit
    -0.08
    ampa
    -0.08
    æĭ¯
    -0.08
     Stevens
    -0.08
    otr
    -0.08
    POSITIVE LOGITS
    çļĦç«ŀäºī
    0.12
    ä¸į认è¯Ĩ
    0.11
    æľ¬èĥ½
    0.11
    èĨı
    0.11
    è§ĴéĢIJ
    0.11
    è¯ĨåĪ«
    0.10
    ç«ŀäºī
    0.10
     territorial
    0.10
    çĶŁæ®ĸ
    0.09
    競çĪŃ
    0.09
    Activations Density 0.172%

    No Known Activations