© 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. 55776
    Prev
    Next
    INDEX
    Explanations

    for instance

    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
    ear
    -0.10
    ëģĶ
    -0.09
     Inst
    -0.09
    çŁ¥ãĤīãģªãģĦ
    -0.09
    Inst
    -0.09
    itudes
    -0.09
    é«®
    -0.09
    orum
    -0.08
    ç¼ĩ
    -0.08
    æĢģ
    -0.08
    POSITIVE LOGITS
    ively
    0.11
    ä¹İ
    0.10
    iveness
    0.09
    halb
    0.09
    elig
    0.09
    ents
    0.08
    ../
    0.08
    amac
    0.08
    æŶæĹ¶å½©
    0.08
    媳
    0.08
    Activations Density 0.024%

    No Known Activations