© 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. 62556
    Prev
    Next
    INDEX
    Explanations

    different from

    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
    åIJĮä¸Ģ
    -0.11
    çłĴ
    -0.10
    èĩ¾
    -0.10
    åIJĮç±»
    -0.10
    å¾Ĺèµ·
    -0.10
     blown
    -0.09
    ä¸įä¸ĭ
    -0.09
    ик
    -0.09
    èĢģèĻİ
    -0.09
     Freedom
    -0.08
    POSITIVE LOGITS
    iable
    0.13
    iates
    0.12
    iating
    0.12
    iability
    0.11
    以å¾Ģ
    0.10
     biá»ĩt
    0.09
    äºİ
    0.09
    ially
    0.09
    ials
    0.09
    iations
    0.09
    Activations Density 0.026%

    No Known Activations