© 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. 5524
    Prev
    Next
    INDEX
    Explanations

    infinite or indefinitely extending concepts

    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
    æ°ĽåĽ´
    -0.09
    ä¸įçŁ¥ä¸įè§ī
    -0.09
    ä¸įå¾Ĺä¸į
    -0.09
    å¾Īæ·±
    -0.08
    å¾Ī强
    -0.08
    å¿«éĢŁ
    -0.08
    ä¸įå¾Ĺä¸į说
    -0.08
    åħ¨éĿ¢èIJ½å®ŀ
    -0.08
    utto
    -0.08
     Bale
    -0.08
    POSITIVE LOGITS
    æĹłéĻIJ
    0.13
    æĹłç©·
    0.12
    âĻ¾
    0.11
    éĢĤ
    0.10
    ä¹ĭ称
    0.10
    æ°¸è¿ľ
    0.10
    Emb
    0.10
    绵
    0.09
     MERCHANTABILITY
    0.09
    æŃī
    0.09
    Activations Density 0.083%

    No Known Activations