© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2128
    Prev
    Next
    INDEX
    Explanations

    reaching and drawing actions

    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
    æĻºåķĨ
    -0.08
    åĬŁ
    -0.08
    éªĭ
    -0.08
     compartment
    -0.08
     Cel
    -0.08
    èĢ¦
    -0.07
     tc
    -0.07
    åı¤ä»Ĭ
    -0.07
     TC
    -0.07
    åħģ
    -0.07
    POSITIVE LOGITS
    伸
    0.17
    伸æīĭ
    0.17
    伸åĩº
    0.14
    姿åĬ¿
    0.12
    æīĭåĬ¿
    0.11
    åĬ¨ä½ľ
    0.11
    é¢Ħå¤ĩ
    0.10
     Montgomery
    0.10
    adium
    0.10
     opi
    0.10
    Activations Density 0.052%

    No Known Activations