© 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. 19957
    Prev
    Next
    INDEX
    Explanations

    is followed by specific words

    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
    å¥Ķæ³¢
    -0.10
    ils
    -0.09
    /or
    -0.09
    æ¢ĵ
    -0.09
    ÑĭÑĪ
    -0.08
    tw
    -0.08
    ä¸Ģçľĭ
    -0.08
    oucher
    -0.08
    ä¸įåłª
    -0.08
    ä¼ı
    -0.08
    POSITIVE LOGITS
    olated
    0.16
    olate
    0.14
    olation
    0.14
    rael
    0.12
    otropic
    0.12
    abelle
    0.10
    otope
    0.10
    alien
    0.09
    pector
    0.09
    è´¨éĩıåĴĮ
    0.09
    Activations Density 0.249%

    No Known Activations