© 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. 58157
    Prev
    Next
    INDEX
    Explanations

    buy

    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
    oppers
    -0.09
    OURCES
    -0.09
    Ñijн
    -0.09
     ÑĨелÑĮÑİ
    -0.09
    ç¹ĩ
    -0.09
    mbH
    -0.08
    nce
    -0.08
    iado
    -0.08
    ëĿ¼ëıĦ
    -0.08
    yu
    -0.08
    POSITIVE LOGITS
    æѤåĪ»
    0.11
    å¾Ĺèµ·
    0.11
    ies
    0.10
    ellow
    0.10
    ä¸įåħĭ
    0.10
    ugin
    0.09
    athon
    0.09
    hea
    0.09
    讫
    0.09
    esterday
    0.09
    Activations Density 0.026%

    No Known Activations