© 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. 7113
    Prev
    Next
    INDEX
    Explanations

    lives of

    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
    iban
    -0.09
    à¹Į
    -0.09
    çĦ¶
    -0.08
    ities
    -0.08
    ized
    -0.08
    åIJįåĪĹ
    -0.08
    ä¼ļåIJĮ
    -0.08
    uba
    -0.08
    scription
    -0.08
    rego
    -0.08
    POSITIVE LOGITS
    ings
    0.11
    nings
    0.10
    INGS
    0.10
    ä¸İæŶ
    0.10
     rÃłng
    0.09
    æĺ
    0.09
    éĵ§
    0.09
    误åĮº
    0.09
    驹
    0.09
    vertise
    0.09
    Activations Density 0.009%

    No Known Activations