© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3134
    Prev
    Next
    INDEX
    Explanations

    model system

    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
     dél
    -0.10
     accompanying
    -0.09
     Saunders
    -0.09
    iglia
    -0.09
    åıijè§ī
    -0.09
    linger
    -0.09
    ][_
    -0.09
    ITS
    -0.09
    çĭ¬
    -0.09
    ä¿Ŀéļľ
    -0.08
    POSITIVE LOGITS
    æ¡Īä¾ĭ
    0.17
    为ä¾ĭ
    0.16
    ä¾ĭåŃIJ
    0.15
    çļĦä¾ĭåŃIJ
    0.14
     exemp
    0.13
    åħ¸èĮĥ
    0.13
     example
    0.13
    示èĮĥ
    0.12
    æ¦ľæł·
    0.12
     exemplary
    0.12
    Activations Density 0.205%

    No Known Activations