© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35765
    Prev
    Next
    INDEX
    Explanations

    GNU Lesser General Public License

    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
    çİĩåħĪ
    -0.11
    ç±³å°Ķ
    -0.10
    ä¹ĭåĬĽ
    -0.09
    çĿģ
    -0.09
    ä¸Ģè§Ī
    -0.09
    _NATIVE
    -0.09
    æĻ®æĥł
    -0.08
    ä¹īä¹Į
    -0.08
    åħ¬å¯ĵ
    -0.08
     conceptual
    -0.08
    POSITIVE LOGITS
     Lesser
    0.11
    ç½ijåıĭè¯Ħ论
    0.09
    utable
    0.08
    åĩºçĤī
    0.08
    çĶ¨é¤IJ
    0.08
     Grace
    0.08
    inger
    0.08
    æİ°
    0.08
    inya
    0.08
    ç»ĻæĤ¨
    0.08
    Activations Density 1.554%

    No Known Activations