© 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. 32740
    Prev
    Next
    INDEX
    Explanations

    McCormack and folding

    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
    ä¸įåıĹ
    -0.09
    æĮĩçĤ¹
    -0.09
    ariat
    -0.09
    indow
    -0.08
    积
    -0.08
    å¾¹
    -0.08
    dden
    -0.08
    å¿ĥå¢ĥ
    -0.08
    _PED
    -0.08
    GINE
    -0.08
    POSITIVE LOGITS
    å¤ĸåĽ´
    0.10
    çģ°å°ĺ
    0.09
     co
    0.09
    äºĮæ°§åĮĸ碳
    0.09
    cord
    0.09
    åĴ¬
    0.09
    å¥ij
    0.09
    è¦ĨçĽĸéĿ¢
    0.09
    ucc
    0.08
    åĮºåĨħ
    0.08
    Activations Density 0.001%

    No Known Activations