© 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. 38021
    Prev
    Next
    INDEX
    Explanations

    announcements after today

    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
     далÑĮÑĪе
    -0.09
    ä¸į说
    -0.09
    0
    -0.08
    3
    -0.08
    7
    -0.08
    /
    -0.08
    6
    -0.08
    4
    -0.08
    ios
    -0.08
    (INPUT
    -0.08
    POSITIVE LOGITS
    宣å¸ĥ
    0.10
    EDIA
    0.10
    antal
    0.09
    ä¸ĸçķĮåIJĦåĽ½
    0.09
    dens
    0.09
    æ¸ħç®Ĺ
    0.09
    ä¸Ģç»Ħ
    0.09
    lexical
    0.09
    æıIJèµ·
    0.09
     Giov
    0.09
    Activations Density 0.043%

    No Known Activations