© 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. 1972
    Prev
    Next
    INDEX
    Explanations

    programming imports and declarations

    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
    éĹ®è¯¢
    -0.08
    æ£ļ
    -0.08
    å¤ļæĸ¹
    -0.08
    åŃļ
    -0.08
    è·¨è¶Ĭ
    -0.07
    èł²
    -0.07
    åĽłåľ°åĪ¶
    -0.07
    æĤ¨åIJĮæĦı
    -0.07
    onom
    -0.07
    èĬĺ
    -0.07
    POSITIVE LOGITS
    urre
    0.09
    ardown
    0.09
    ä»Ģä¹Īåij¢
    0.09
    è¿Ļ份
    0.09
    .gwt
    0.09
    ooke
    0.09
    adden
    0.09
    URRE
    0.09
    ideo
    0.08
    ACES
    0.08
    Activations Density 0.028%

    No Known Activations