© 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. 21983
    Prev
    Next
    INDEX
    Explanations

    introduction markers

    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
    åĪ©åĻ¨
    -0.09
    spot
    -0.09
    åħ·ä½ĵçļĦ
    -0.08
    ç»ĨèĬĤ
    -0.08
    åį«
    -0.08
    ä¹ĥèĩ³
    -0.08
    åĮĸ
    -0.08
    åħ·ä½ĵ
    -0.08
    æĸĹ
    -0.08
    äºķ
    -0.08
    POSITIVE LOGITS
    èĥĮæĻ¯
    0.17
    æ¦Ĥè¿°
    0.14
    ä»ĭç»į
    0.12
     background
    0.12
    æħ¨
    0.12
    /background
    0.11
    ä»ĭç»įäºĨ
    0.11
    ä»ĭç»įä¸Ģä¸ĭ
    0.11
    ç®Ģä»ĭ
    0.11
    ä»ĭç´¹
    0.11
    Activations Density 0.778%

    No Known Activations