© 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. 1495
    Prev
    Next
    INDEX
    Explanations

    Cadillac Ranch

    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
    <<<
    -0.09
    spr
    -0.09
    lang
    -0.08
    ä»ĵ
    -0.08
    Pocket
    -0.08
    æĬ¥éħ¬
    -0.08
    妥
    -0.08
    éĶ¦
    -0.08
    Spr
    -0.08
    缸åıį
    -0.08
    POSITIVE LOGITS
    çĻ½æ²Ļ
    0.11
    饯
    0.10
    yers
    0.10
    ä¸Ģéĥ¨
    0.09
    æĥĬèī³
    0.09
    ä¹ĭ乡
    0.09
    人æīįåŁ¹åħ»
    0.09
     ÑĥÑģÑĤановлен
    0.09
    èĭ
    0.09
    Orm
    0.09
    Activations Density 0.003%

    No Known Activations