© 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. 34917
    Prev
    Next
    INDEX
    Explanations

    task-related nouns followed by 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
    aster
    -0.09
    èĥ½å¾ĹåĪ°
    -0.08
     بص
    -0.08
    åıĮçľ¼
    -0.08
    0
    -0.08
    è¿ľç¦»
    -0.08
    Examples
    -0.08
    å¾ĹåĪ°äºĨ
    -0.08
    èĥ½æ»¡è¶³
    -0.08
    åıĹéĻIJ
    -0.08
    POSITIVE LOGITS
    è¦ģèĢĥèĻij
    0.12
    è¦ģåıĬæŶ
    0.11
    è¦ģåİ»
    0.11
    è¦ģåĬłå¼º
    0.11
    è¦ģ好好
    0.11
    è¦ģçľĭ
    0.10
    åĢ¼å¾Ĺ
    0.10
     нÑĥжно
    0.09
    åľ°æĸ¹
    0.09
    ä»»åĬ¡
    0.09
    Activations Density 0.125%

    No Known Activations