© 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. 62646
    Prev
    Next
    INDEX
    Explanations

    only

    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
     LIC
    -0.10
    çIJĨ解åĴĮ
    -0.09
    éķĸ
    -0.09
    خب
    -0.08
    é¦ĸ次
    -0.08
    å°Ĩè¿Ľä¸ĢæŃ¥
    -0.08
    å°ĨæĪIJ为
    -0.08
    ä½£
    -0.08
    imentary
    -0.08
    /lic
    -0.08
    POSITIVE LOGITS
    羣æŃ£
    0.15
     truly
    0.12
     EVER
    0.12
    åĶ¯æľī
    0.11
    åĶ¯
    0.11
    ä¾ĭå¤ĸ
    0.11
     ever
    0.11
    å°º
    0.11
    åĶ¯ä¸Ģ
    0.10
    æĥŁ
    0.10
    Activations Density 0.079%

    No Known Activations