© 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. 9215
    Prev
    Next
    INDEX
    Explanations

    at the

    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
    æīĢè°ĵ
    -0.12
    æīĢè¬Ĥ
    -0.11
    æīĢè°ĵçļĦ
    -0.10
    mediately
    -0.09
    ëį°
    -0.09
     ÑĢей
    -0.09
    å¾ĪæŃ£å¸¸
    -0.09
    sofar
    -0.09
    éªij
    -0.09
    å¹²èĦĨ
    -0.09
    POSITIVE LOGITS
    æľīçļĦ
    0.12
    usch
    0.09
    ención
    0.09
    è¿Ļä¹Łæĺ¯
    0.09
    semble
    0.08
    kinson
    0.08
    lassian
    0.08
    æľīä¸ĢçĤ¹
    0.08
    onium
    0.08
    ä¸ĢåĪĨéĴŁ
    0.08
    Activations Density 0.054%

    No Known Activations