© 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. 62393
    Prev
    Next
    INDEX
    Explanations

    more or less than

    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
    åįĩèµ·
    -0.09
    stor
    -0.08
    顽强
    -0.08
    âĢ¥
    -0.08
    éģ
    -0.08
     bullied
    -0.08
    èĭ¥å¹²
    -0.08
    cade
    -0.08
    fer
    -0.08
    etri
    -0.08
    POSITIVE LOGITS
    alem
    0.11
    æģ°æģ°
    0.10
    æł·åŃIJ
    0.09
    çķª
    0.09
    xious
    0.09
    Synopsis
    0.08
    ula
    0.08
    çĿij
    0.08
     Ziel
    0.08
    è¿İæĿ¥äºĨ
    0.08
    Activations Density 0.040%

    No Known Activations