© 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. 5055
    Prev
    Next
    INDEX
    Explanations

    springs and wells

    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
    èĬ¸
    -0.10
    åŁİéķĩåĮĸ
    -0.10
    é£ŀæī¬
    -0.10
    æĴķ
    -0.10
    urge
    -0.09
    é£ŀç¿Ķ
    -0.09
    第ä¸Ģéĥ¨
    -0.09
    éĿ
    -0.08
    avad
    -0.08
    åıĺçİ°
    -0.08
    POSITIVE LOGITS
    æ³īæ°´
    0.23
    æ³ī
    0.22
    äºķ
    0.15
     fountain
    0.14
    æºIJæ³ī
    0.14
     wells
    0.13
    æ°´éĩı
    0.13
    涸
    0.12
    æ°´æºIJ
    0.12
    温æ³ī
    0.11
    Activations Density 0.089%

    No Known Activations