© 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. 62484
    Prev
    Next
    INDEX
    Explanations

    athletes including disabled veterans

    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
    ular
    -0.10
    ample
    -0.10
    大çīĩ
    -0.09
    iso
    -0.09
    aries
    -0.09
    ä¸įæ¸ħ
    -0.09
    AME
    -0.09
    å·¥ç¨ĭè´¨éĩı
    -0.09
    好人
    -0.09
    edly
    -0.08
    POSITIVE LOGITS
    ically
    0.13
    çĶ¨åĵģ
    0.12
    gether
    0.11
    ÑĤай
    0.11
    letes
    0.10
    ropolis
    0.10
    ä»»ä½ķæŶåĢĻ
    0.10
    istic
    0.10
    ched
    0.10
    éĻµ
    0.09
    Activations Density 0.012%

    No Known Activations