© 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. 63318
    Prev
    Next
    INDEX
    Explanations

    man or males

    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
    çĶ·å¥³
    -0.12
    女åŃ©åŃIJ
    -0.12
    女æĸ¹
    -0.12
    女çĶŁ
    -0.12
    è·Łå¥¹
    -0.11
    女主è§Ĵ
    -0.10
    å°ij女
    -0.10
    女主
    -0.10
    çļĦ女人
    -0.10
     females
    -0.10
    POSITIVE LOGITS
    æ£ķèī²
    0.09
    illac
    0.08
     Pep
    0.08
    ipers
    0.08
    spy
    0.08
    iscal
    0.08
    èĨı
    0.08
    èĽĬ
    0.07
     perspective
    0.07
    alf
    0.07
    Activations Density 0.119%

    No Known Activations