© 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. 30789
    Prev
    Next
    INDEX
    Explanations

    mimosa or iminate

    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
    æ³Ĭ
    -0.09
    uard
    -0.09
    享
    -0.08
    åĭ¿
    -0.08
    å±Ļ
    -0.08
    _Build
    -0.08
    æ²½
    -0.08
    åģľ
    -0.08
    å±Ģ
    -0.08
    mares
    -0.08
    POSITIVE LOGITS
    å¤įæ´»
    0.10
    ãģıãĤĮ
    0.09
    檬
    0.09
    ç»ij
    0.09
    èįĨå·ŀ
    0.09
    çĭ°
    0.09
    çijĽ
    0.08
    imo
    0.08
    äº§åľ°
    0.08
    ient
    0.08
    Activations Density 0.066%

    No Known Activations