© 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. 62263
    Prev
    Next
    INDEX
    Explanations

    existence

    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
    OUN
    -0.11
    stry
    -0.11
    ç»ĩ
    -0.09
    ailable
    -0.09
    atura
    -0.09
    sters
    -0.09
    oun
    -0.09
    TURE
    -0.09
    ä¼ģåĽ¾
    -0.09
    ếp
    -0.08
    POSITIVE LOGITS
    entially
    0.11
    entials
    0.10
    اء
    0.10
    emple
    0.10
    æĶ¹éĿ©å§Ķ
    0.09
    ively
    0.09
    ional
    0.09
    .CONFIG
    0.09
    baum
    0.09
    -minded
    0.09
    Activations Density 0.030%

    No Known Activations