© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20810
    Prev
    Next
    INDEX
    Explanations

    ethanolic extracts of leaves

    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
    èĬĿ
    -0.10
    acher
    -0.09
    allen
    -0.09
    otte
    -0.08
    elight
    -0.08
     Swe
    -0.08
    çĽĺ
    -0.08
    ghi
    -0.08
    Nib
    -0.08
    Fcn
    -0.08
    POSITIVE LOGITS
    åĪ¶æĪIJ
    0.11
    丰ç¡ķ
    0.10
    治好
    0.10
    è¿ij代
    0.09
    _Anim
    0.09
    ãĤ¤ãĥ©
    0.09
    çħ¸
    0.09
    å¾Ĵ
    0.09
    éĴ±è´¢
    0.09
    çī¹ä»·
    0.09
    Activations Density 0.196%

    No Known Activations