© 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. 5428
    Prev
    Next
    INDEX
    Explanations

    intestinal disorders

    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
    榫
    -0.09
    AWN
    -0.09
    .Skin
    -0.08
    èıĸ
    -0.08
    æĻĴ
    -0.08
    èĨ¦
    -0.08
    å¾Ĥ
    -0.08
    skin
    -0.08
    åħķ
    -0.08
    OLDER
    -0.08
    POSITIVE LOGITS
    粪
    0.12
    èħ¹
    0.11
    èħ¹éĥ¨
    0.11
    èĤļ
    0.10
    ä¹ĥ
    0.10
    åĹĿ
    0.10
     fec
    0.09
    åĹ³
    0.09
    ħĮ
    0.09
    åħ³èģĶ交æĺĵ
    0.09
    Activations Density 0.838%

    No Known Activations