© 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. 22473
    Prev
    Next
    INDEX
    Explanations

    really nice

    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
    æŃ»åİ»
    -0.09
    åĩºèī²
    -0.09
    IFn
    -0.09
    ROY
    -0.09
    .getvalue
    -0.09
    ä»Ĩ
    -0.09
    /cgi
    -0.08
    ErrMsg
    -0.08
    åľ¨åĮĹ京
    -0.08
    éĥ½æľīçĿĢ
    -0.08
    POSITIVE LOGITS
    æīĢ以说
    0.09
    çıł
    0.09
    arios
    0.09
    å¿ĹæĦ¿èĢħ
    0.08
    æĪ¿
    0.08
    éű
    0.08
    åı¯è§Ĥ
    0.08
    èĩªæĦ¿
    0.08
    æģĴ
    0.08
    就说
    0.08
    Activations Density 0.050%

    No Known Activations