© 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. 4804
    Prev
    Next
    INDEX
    Explanations

    protruding, extending, outward

    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
    æĿ³
    -0.09
     unknown
    -0.09
    ä¹Łä¸įçŁ¥éģĵ
    -0.09
    æľªçŁ¥
    -0.08
    å¾Ń
    -0.08
     Unknown
    -0.08
     CSR
    -0.08
     Ñģебе
    -0.08
     floor
    -0.08
    æ±ĩ
    -0.08
    POSITIVE LOGITS
    éľ²åĩº
    0.14
    æļ´éľ²
    0.13
    éľ²
    0.12
    åĩºæĿ¥äºĨ
    0.11
    åĩºæĿ¥çļĦ
    0.11
    åĩºæĿ¥
    0.10
    angu
    0.10
    äºĨåĩºæĿ¥
    0.10
    ä¸įåĩº
    0.10
    åľ¨å¤ĸéĿ¢
    0.10
    Activations Density 0.222%

    No Known Activations