© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50791
    Prev
    Next
    INDEX
    Explanations

    about, almost, nearly, least

    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
    rek
    -0.10
    åį¡éĢļ
    -0.10
    为äºĨæĽ´å¥½
    -0.09
    _blob
    -0.09
    æľªå¿ħ
    -0.09
    quin
    -0.09
    æľ¬äºº
    -0.09
    注æĺİ
    -0.08
    STER
    -0.08
    çĶļ
    -0.08
    POSITIVE LOGITS
    大éĥ¨åĪĨ
    0.10
    TURE
    0.10
    å°¼äºļ
    0.09
    èĦIJ
    0.09
    èĴ
    0.09
    æij¸
    0.08
    åĵij
    0.08
    çŁ£
    0.08
    RY
    0.08
    alc
    0.08
    Activations Density 0.111%

    No Known Activations