© 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. 32739
    Prev
    Next
    INDEX
    Explanations

    lacks information or ability

    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
    æĶ»åĬ¿
    -0.10
    tas
    -0.10
    aly
    -0.09
    eming
    -0.09
    åIJ¸åıĸ
    -0.09
    tering
    -0.09
    åIJĬ
    -0.09
    ÙģاÙĤ
    -0.08
    chest
    -0.08
    åıĺäºĨ
    -0.08
    POSITIVE LOGITS
    redo
    0.10
    cpy
    0.09
    _RESOLUTION
    0.09
    üb
    0.09
    éªģ
    0.09
    ena
    0.09
    оÑĩнÑĭй
    0.09
    ives
    0.09
    è¨İ
    0.08
    udo
    0.08
    Activations Density 0.006%

    No Known Activations