© 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. 37229
    Prev
    Next
    INDEX
    Explanations

    Itanium

    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
    讥
    -0.10
    jis
    -0.08
    uten
    -0.08
    个æĢ§
    -0.08
    为主è¦ģ
    -0.08
    ·»
    -0.08
    safe
    -0.08
    ëıĮ
    -0.08
    éĥ½ä¸įçŁ¥éģĵ
    -0.08
    .Generated
    -0.08
    POSITIVE LOGITS
    .Names
    0.10
    ä¸ĢåłĨ
    0.09
    ä¸ĢçĶŁ
    0.09
    linger
    0.08
     Jackson
    0.08
    è¢Ī
    0.08
    -board
    0.08
    å¨ĺ家
    0.08
    彤
    0.08
    UIScreen
    0.08
    Activations Density 0.026%

    No Known Activations