© 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. 33214
    Prev
    Next
    INDEX
    Explanations

    real-time

    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
    erial
    -0.09
    andom
    -0.09
    -school
    -0.09
    CodeGen
    -0.09
    æ¦Ľ
    -0.08
    USA
    -0.08
    dl
    -0.08
    ì§ĵ
    -0.08
    erg
    -0.08
    é»Ħå±±
    -0.08
    POSITIVE LOGITS
    aneously
    0.12
     rÃłng
    0.11
    -ish
    0.10
    ais
    0.10
    è¿Ļ对
    0.09
    vely
    0.09
    å¹²éĥ¨éĺŁä¼į
    0.09
    ä»İ严
    0.09
    æľĽåİ»
    0.08
    RULE
    0.08
    Activations Density 0.015%

    No Known Activations