© 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. 18929
    Prev
    Next
    INDEX
    Explanations

    turn the, turn on

    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
     Tender
    -0.09
    URN
    -0.09
    eward
    -0.09
    arend
    -0.09
    æģ¸
    -0.09
    	TokenName
    -0.09
    ä¸Ģå®ļç¨ĭ度
    -0.09
     tender
    -0.08
    /out
    -0.08
    åıĸè¯ģ
    -0.08
    POSITIVE LOGITS
    stile
    0.13
    ning
    0.12
    pike
    0.11
    table
    0.10
    tables
    0.10
    åħ¸ç¤¼
    0.10
    backs
    0.09
    åijIJ
    0.09
    ned
    0.09
    åĿıäºĭ
    0.09
    Activations Density 0.043%

    No Known Activations