© 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. 33296
    Prev
    Next
    INDEX
    Explanations

    prairie

    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
    teenth
    -0.09
    åĺİ
    -0.09
    ÑĤика
    -0.09
    æĪĽ
    -0.09
     intervening
    -0.08
    å°¼æĸ¯
    -0.08
    urd
    -0.08
    æĢ§åij½
    -0.08
    éĹ³
    -0.08
    ible
    -0.08
    POSITIVE LOGITS
    -born
    0.11
    hawks
    0.10
    èĩ¾
    0.09
    æ·±åİļ
    0.09
    eur
    0.09
    bau
    0.08
    aus
    0.08
    é£İåħī
    0.08
    errat
    0.08
    issent
    0.08
    Activations Density 0.004%

    No Known Activations