© 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. 48660
    Prev
    Next
    INDEX
    Explanations

    Broncos

    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
    åŁ´
    -0.10
    第äºĮç§į
    -0.10
    icular
    -0.10
    ëģĶ
    -0.10
    ISON
    -0.09
    _lazy
    -0.09
    楣
    -0.09
    çĤ½
    -0.09
    åŀ£
    -0.09
    åħļæĢ»
    -0.09
    POSITIVE LOGITS
    ä»Ħ
    0.09
    èĩ¾
    0.09
    vÃŃ
    0.09
    нев
    0.09
    inality
    0.09
    ettes
    0.09
    agne
    0.09
    é¦ģ
    0.08
    iÄĻ
    0.08
    Unsigned
    0.08
    Activations Density 0.017%

    No Known Activations