© 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. 57087
    Prev
    Next
    INDEX
    Explanations

    stars, galaxies, solar systems

    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
    å¸ĺ
    -0.09
    ä½ĵåĪ¶æľºåĪ¶
    -0.09
    reh
    -0.09
     ePub
    -0.09
    èī¯ãģı
    -0.08
    mez
    -0.08
    åĮ¡
    -0.08
     Hicks
    -0.08
    udes
    -0.08
    ipmap
    -0.08
    POSITIVE LOGITS
    éģ¥è¿ľ
    0.09
    æ»Ĥ
    0.09
    éĢļè¡Į
    0.09
    æį¢äºĨ
    0.09
    9
    0.09
     stars
    0.09
     burg
    0.08
    ansa
    0.08
    lit
    0.08
    vern
    0.08
    Activations Density 0.049%

    No Known Activations