© 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. 49472
    Prev
    Next
    INDEX
    Explanations

    by what

    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
    为人
    -0.11
    çĶ±
    -0.11
     Hamp
    -0.10
    åIJİæŀľ
    -0.09
    .normalize
    -0.09
    ина
    -0.09
    åIJİåĨį
    -0.09
    ÑĢок
    -0.09
    ductor
    -0.09
    æģ¤
    -0.09
    POSITIVE LOGITS
    è¡·
    0.16
     virtue
    0.16
     means
    0.14
    è¿Ļç§įæĸ¹å¼ı
    0.14
    -election
    0.12
     mistake
    0.12
     dint
    0.12
     analogy
    0.12
    products
    0.10
    entifier
    0.10
    Activations Density 0.428%

    No Known Activations