© 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. 32847
    Prev
    Next
    INDEX
    Explanations

    works well or fine

    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
    çĿ¨
    -0.10
    çĶŁæŃ»
    -0.09
    羯
    -0.09
    izz
    -0.08
    èĥ½å¤Łåľ¨
    -0.08
    æµĶ
    -0.08
    dj
    -0.08
    åĮĹç¾İ
    -0.08
    é£İæ³¢
    -0.08
     اÙĦعاÙĦÙħÙĬ
    -0.07
    POSITIVE LOGITS
    åĬ²
    0.10
    feeds
    0.10
    IFO
    0.09
     Masc
    0.09
    Į¨
    0.09
    èıĮ
    0.09
    ropp
    0.09
    å¼Ģå±Ģ
    0.09
    çīµæīĭ
    0.09
    æļ¾
    0.08
    Activations Density 0.060%

    No Known Activations