© 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. 27585
    Prev
    Next
    INDEX
    Explanations

    private collections and former owners

    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
     Hole
    -0.08
     Alley
    -0.08
    çħ
    -0.08
    åĬłæ²¹ç«Ļ
    -0.08
    åĶ¤
    -0.08
    schlä
    -0.08
     Pub
    -0.08
    Pub
    -0.08
    лÑij
    -0.08
     Shack
    -0.08
    POSITIVE LOGITS
    æĶ¶èĹı
    0.14
    åı¦ä¸Ģä½į
    0.12
    ç§ģ人
    0.11
     ìĪĺì§ij
    0.11
     Collector
    0.10
    collector
    0.10
    èĴIJéĽĨ
    0.10
     collections
    0.10
     collectors
    0.10
    积èĵĦ
    0.10
    Activations Density 0.101%

    No Known Activations