© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8883
    Prev
    Next
    INDEX
    Explanations

    consent to or for

    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
    æ²¥
    -0.10
    inary
    -0.09
    lying
    -0.09
    hood
    -0.09
    æīĴ
    -0.09
    ä½ķåĨµ
    -0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.08
    째
    -0.08
    tek
    -0.08
    åĨįä¸Ģ次
    -0.08
    POSITIVE LOGITS
    åĴĮæĶ¯æĮģ
    0.14
    ably
    0.12
    ively
    0.11
    ucky
    0.10
    erves
    0.10
    ience
    0.10
    geber
    0.09
    encia
    0.09
    åŃº
    0.09
    atory
    0.09
    Activations Density 0.018%

    No Known Activations