© 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. 18289
    Prev
    Next
    INDEX
    Explanations

    stretching, movements, and yawning

    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
    PAL
    -0.09
    alis
    -0.09
    äºī缸
    -0.09
    çı°
    -0.09
    afi
    -0.09
    å®īæĬļ
    -0.09
    Walker
    -0.08
    _ssl
    -0.08
    abal
    -0.08
    åŁ¹åħ»åѦçĶŁ
    -0.08
    POSITIVE LOGITS
    åĹ½
    0.12
    åĴ³åĹ½
    0.11
     yaw
    0.11
    åļı
    0.11
    åı¹æģ¯
    0.10
    åľī
    0.10
    åħ¬å¸ĥçļĦ
    0.10
    èĭ¦ç¬ij
    0.09
    å¼Ģåĩº
    0.09
    以åĨħ
    0.09
    Activations Density 0.167%

    No Known Activations