© 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. 49249
    Prev
    Next
    INDEX
    Explanations

    abstract components and states

    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
    sheets
    -0.09
    ç»į
    -0.09
    ä¸įåIJĮç±»åŀĭ
    -0.09
    踵
    -0.09
    аÑı
    -0.09
    nob
    -0.09
    andra
    -0.09
    angement
    -0.09
    OPTION
    -0.08
    ÅĤaw
    -0.08
    POSITIVE LOGITS
    们
    0.27
    们çļĦ
    0.27
    åĢij
    0.25
    (s
    0.20
    sWith
    0.19
    们éĥ½
    0.19
    ëĵ¤ìĿĢ
    0.18
    ëĵ¤ìĿ´
    0.17
    sto
    0.17
    ëĵ¤
    0.16
    Activations Density 1.492%

    No Known Activations