© 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. 62768
    Prev
    Next
    INDEX
    Explanations

    chocolate chips

    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
    æĩĭ
    -0.12
    漫
    -0.10
    éľİ
    -0.10
    رÙģ
    -0.09
    è·¨
    -0.09
    é¡·
    -0.09
    ä¸Ģä¼ļ
    -0.09
    ëŀĢ
    -0.09
    tl
    -0.09
    çĪĩ
    -0.08
    POSITIVE LOGITS
    ANTE
    0.10
    ëį°
    0.08
    åıįè¿ĩæĿ¥
    0.08
     filesize
    0.08
    åģ¿
    0.08
     conc
    0.08
    èĬ±çĵ£
    0.08
    åĥįãģį
    0.08
    å°Ĭéĩį
    0.08
     enlisted
    0.07
    Activations Density 0.005%

    No Known Activations