© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9696
    Prev
    Next
    INDEX
    Explanations

    fractions and percentages

    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
    ãģªãģĬ
    -0.09
    款
    -0.09
    æ°´æĻ¶
    -0.08
     Nó
    -0.08
    ÑĭÑħ
    -0.08
    强è¡Į
    -0.08
     Sawyer
    -0.08
    ä¸Ģ个èģĮä¸ļ
    -0.08
    ificador
    -0.08
     wash
    -0.08
    POSITIVE LOGITS
    åı»
    0.10
    oul
    0.09
    æļ¹
    0.08
    ÑĤик
    0.08
    UDO
    0.08
    iram
    0.08
    篦
    0.08
     Bers
    0.08
    侯
    0.08
    æĺİç¡®äºĨ
    0.08
    Activations Density 0.046%

    No Known Activations