© 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. 31792
    Prev
    Next
    INDEX
    Explanations

    can followed by a verb

    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
    IRM
    -0.11
    æ¾į
    -0.10
    ä»ħ为
    -0.09
    åıªä¸º
    -0.09
    èĤĮèĤ¤
    -0.09
    pez
    -0.09
    irmed
    -0.09
    æłı
    -0.08
    obra
    -0.08
    allele
    -0.08
    POSITIVE LOGITS
    çijĽ
    0.09
    cup
    0.09
     Ñģамого
    0.09
    elen
    0.09
    è´¡çĮ®åĬĽéĩı
    0.08
    eng
    0.08
    åĩ«
    0.08
    æĦıæĥ³ä¸įåĪ°
    0.08
    ston
    0.08
    èĬĻ
    0.08
    Activations Density 0.019%

    No Known Activations