© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21599
    Prev
    Next
    INDEX
    Explanations

    first-class cricketer

    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
    ç¾½
    -0.11
    åĨ·
    -0.09
     leggings
    -0.09
    ander
    -0.09
    éĶ£
    -0.08
     nailed
    -0.08
    nom
    -0.08
    åįģä¸īæĿ¡
    -0.08
    åı·
    -0.08
    quire
    -0.08
    POSITIVE LOGITS
    课å¤ĸ
    0.11
    头顶
    0.10
    çĥĤ
    0.09
    _totals
    0.09
    iores
    0.08
    ktion
    0.08
    çĶŁçĶŁ
    0.08
    æĭīåĬ¨
    0.08
    isel
    0.08
    åıijæĮ¥
    0.08
    Activations Density 0.136%

    No Known Activations