© 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. 33288
    Prev
    Next
    INDEX
    Explanations

    nothing but something

    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
    ä»Ģä¹Īåij¢
    -0.09
    äºĭ项
    -0.09
    ething
    -0.09
    è¾ħ
    -0.09
    OME
    -0.08
    åİĨåı²æĤłä¹ħ
    -0.08
    things
    -0.08
     ÐŁÐ¾Ñĩ
    -0.08
     something
    -0.08
    something
    -0.08
    POSITIVE LOGITS
    åĩ¡æľ¬ç½ij
    0.09
    ä¸ĢèĪ¬æĿ¥è¯´
    0.09
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.09
    好è¯Ħ
    0.09
     Palin
    0.08
    åıįåĵį
    0.08
    è£Ĩ
    0.08
    åģļå¾Ĺ
    0.08
    åħ¬åijĬ称
    0.08
    cÃŃ
    0.08
    Activations Density 0.027%

    No Known Activations