© 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. 2336
    Prev
    Next
    INDEX
    Explanations

    black and white

    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
    aille
    -0.10
    /operator
    -0.10
    æĹºçĽĽ
    -0.10
    æ¼Ķ
    -0.09
    æ´
    -0.08
    itary
    -0.08
     caves
    -0.08
    éĽį
    -0.08
    å¦Ĥä½ķåİ»
    -0.08
    allas
    -0.08
    POSITIVE LOGITS
    åĪĨæĺİ
    0.09
     Lyn
    0.08
    ãģ©
    0.08
    ä¹ĭäºī
    0.08
    çĿ£å¯¼
    0.08
    im
    0.08
    èĩªå¦Ĥ
    0.08
    athan
    0.08
    é»ijçĻ½
    0.08
    uchen
    0.08
    Activations Density 0.004%

    No Known Activations