© 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. 48758
    Prev
    Next
    INDEX
    Explanations

    asteroid and plants

    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
    éĺĹ
    -0.12
    abel
    -0.09
    Ñĩик
    -0.09
    affe
    -0.08
    ish
    -0.08
    Å¡t
    -0.08
    è¢Ī
    -0.08
    ialis
    -0.08
    æ¸į
    -0.08
    æѤäºĭ
    -0.08
    POSITIVE LOGITS
    ä¸ļä½Ļ
    0.09
    acus
    0.09
     ÑģебÑı
    0.09
    à¹īà¸Ļ
    0.08
    lah
    0.08
    most
    0.08
    èĻĵ
    0.08
    ipation
    0.08
    gres
    0.08
    icker
    0.08
    Activations Density 0.041%

    No Known Activations