© 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. 49803
    Prev
    Next
    INDEX
    Explanations

    case is true

    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
    æľīåIJį
    -0.10
    被çĽĹ
    -0.10
    å»ĵ
    -0.09
    亢
    -0.09
    æľĢåħ³éĶ®
    -0.08
    æīĵå¾Ĺ
    -0.08
    icky
    -0.08
    åŀ©
    -0.08
    åŁ
    -0.08
    åĹij
    -0.08
    POSITIVE LOGITS
    弦
    0.10
    ä¹ĭæŶ
    0.09
    æĥħåĨµè¿Ľè¡Į
    0.09
    é«¡
    0.09
    _LS
    0.09
    _spacing
    0.09
    è¿Ļç§įæĥħåĨµ
    0.09
    >true
    0.09
    åĽŀäºĭ
    0.09
     rar
    0.08
    Activations Density 0.069%

    No Known Activations