© 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. 49438
    Prev
    Next
    INDEX
    Explanations

    thanks in advance

    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
    é«ĺåİĭ
    -0.09
    åıªæĺ¯ä¸ºäºĨ
    -0.09
    æĢ»æľī
    -0.09
    浸
    -0.09
    究竣æĺ¯
    -0.09
    æ·Ģ
    -0.09
    åı®
    -0.09
    åĬłæ²¹
    -0.09
    éªł
    -0.09
    åĴ¬
    -0.09
    POSITIVE LOGITS
    ç¥ĸåĽ½
    0.09
    åIJĦä½į
    0.08
     TCL
    0.08
     Burr
    0.08
    æijħ
    0.08
    Č
    0.08
    ç¬Ħ
    0.08
    ably
    0.08
    ely
    0.08
    éĢĭ
    0.07
    Activations Density 0.005%

    No Known Activations