© 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. 50164
    Prev
    Next
    INDEX
    Explanations

    salami publishing, bit-rot, grinding

    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
    ç»İ
    -0.09
    ä¸įè§ģ
    -0.08
    è¯Ļ
    -0.08
    cente
    -0.08
    longleftrightarrow
    -0.08
    æµģè¡ĮçļĦ
    -0.08
     ReactDOM
    -0.08
    PREFIX
    -0.08
    ä»ĸ说
    -0.08
    ugo
    -0.08
    POSITIVE LOGITS
    пан
    0.10
    满满
    0.09
    çħ§
    0.09
    è´Łè´£ä»»
    0.09
    å±¥
    0.09
    rez
    0.08
    é¢ijçİĩ
    0.08
    bish
    0.08
    ottom
    0.08
    áºŃn
    0.08
    Activations Density 0.144%

    No Known Activations