© 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. 18117
    Prev
    Next
    INDEX
    Explanations

    analysis or commentary

    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
    åIJĪä½ľ
    -0.09
    å®ŀéªĮ
    -0.09
    ä¼ļ计
    -0.09
    æīģ
    -0.09
    宽带
    -0.09
    æĿĵ
    -0.09
    getJSON
    -0.08
     EXPER
    -0.08
    交代
    -0.08
    mans
    -0.08
    POSITIVE LOGITS
    å±ĢåĬ¿
    0.10
    è§Ĥå¯Ł
    0.10
    èĪĨæĥħ
    0.10
    çłĶåĪ¤
    0.09
    åĪĨæŀIJ
    0.09
    èѦæĥķ
    0.09
    éĢĤæŶ
    0.09
    çı£
    0.09
    _OBS
    0.09
    åijĺ
    0.09
    Activations Density 0.088%

    No Known Activations