© 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. 61023
    Prev
    Next
    INDEX
    Explanations

    Center for

    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
    ager
    -0.10
    ifi
    -0.09
    ä»Ĺ
    -0.09
     Bris
    -0.08
    SOR
    -0.08
    oller
    -0.08
    uka
    -0.08
    ilet
    -0.08
    è¸ıåħ¥
    -0.08
    ewe
    -0.08
    POSITIVE LOGITS
    åĶ§
    0.10
    à¹Ģà¸ĭ
    0.09
    æĸ°éĹ»åıijå¸ĥ
    0.09
    ä¸Ģ个éĹ®é¢ĺ
    0.08
    pher
    0.08
    æĪĸå¤ļ
    0.08
    éĺĸ
    0.08
    sell
    0.08
     DECL
    0.08
    çļĦéĤ£ä¸ª
    0.08
    Activations Density 0.014%

    No Known Activations