© 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. 2893
    Prev
    Next
    INDEX
    Explanations

    email domains and identifiers

    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
    Ùĩ
    -0.13
    dır
    -0.13
    e
    -0.12
    Ùħ
    -0.11
    ¤
    -0.11
    h
    -0.11
    许å¤ļ
    -0.11
    ìĶ©
    -0.11
    l
    -0.10
    ми
    -0.10
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.13
    0.13
    unct
    0.10
    èĥ¥
    0.09
    ذا
    0.09
    à¹Į
    0.09
    ãģıãĤĮ
    0.09
    ï¸ı
    0.09
    inel
    0.09
    ãģĵãģĵãģ¾ãģ§
    0.08
    Activations Density 1.178%

    No Known Activations