© 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. 36894
    Prev
    Next
    INDEX
    Explanations

    after commas and periods

    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
    lesh
    -0.10
    èĩªè¡Į
    -0.09
    athers
    -0.09
    æµij
    -0.09
    æĢĴ
    -0.08
    frm
    -0.08
    ç«
    -0.08
     voluntary
    -0.08
    å¹ķ
    -0.08
    éĻIJ度
    -0.08
    POSITIVE LOGITS
    è´²
    0.10
    IZER
    0.10
    æĶĴ
    0.09
    .gnu
    0.09
    ç±³ç²ī
    0.09
    erin
    0.09
    ترة
    0.09
     outr
    0.08
    æĪIJé¾Ļ
    0.08
     ìłij
    0.08
    Activations Density 0.096%

    No Known Activations