© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7422
    Prev
    Next
    INDEX
    Explanations

    package installation instructions

    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
    大å®Ĺ
    -0.09
    abad
    -0.09
    ubbo
    -0.09
    èĬĻ
    -0.09
     WARN
    -0.09
    avin
    -0.09
    ISTS
    -0.08
    даÑĩи
    -0.08
    gart
    -0.08
    ä¹ĭåħ§å®¹
    -0.08
    POSITIVE LOGITS
    æīĢéľĢçļĦ
    0.11
    ä¼´ä¾£
    0.09
    æīĢéľĢ
    0.09
     easiest
    0.09
    åı¯åľ¨
    0.09
    åħ¨å®¶
    0.09
    åħ¨å¥Ĺ
    0.08
    orest
    0.08
    нÑģÑĤ
    0.08
    fits
    0.08
    Activations Density 0.555%

    No Known Activations