© 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. 49261
    Prev
    Next
    INDEX
    Explanations

    made appearances, played matches

    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
    åIJ¸åıĸ
    -0.11
    éĢIJ
    -0.09
    æIJŀå¾Ĺ
    -0.09
    æĦ§
    -0.09
    èµĦæºIJä¼ĺåĬ¿
    -0.09
     Suspension
    -0.09
    æ°Ķæ°Ľ
    -0.08
    å¼Ħå¾Ĺ
    -0.08
     kuk
    -0.08
    åīij
    -0.08
    POSITIVE LOGITS
    å®Ĺ
    0.10
    nette
    0.09
    èĻ«
    0.09
    çĸ£
    0.09
    aris
    0.09
    uran
    0.08
    ÃŃn
    0.08
    Loan
    0.08
     Earn
    0.08
    TRS
    0.08
    Activations Density 0.308%

    No Known Activations