© 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. 39523
    Prev
    Next
    INDEX
    Explanations

    natural world and resources

    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
    zilla
    -0.10
    orama
    -0.10
    èĩªèº«çļĦ
    -0.09
    æĭĪ
    -0.09
    æļ®
    -0.09
    åIJİåĭ¤
    -0.09
    楫
    -0.09
    naires
    -0.09
    icit
    -0.09
    å¼ıçļĦ
    -0.08
    POSITIVE LOGITS
    aleza
    0.11
    mente
    0.09
    istic
    0.09
    èijĨ
    0.08
    è³ĩæºIJ
    0.08
    adays
    0.08
     upd
    0.08
    verständlich
    0.08
    ãĤŃãĥ³
    0.08
    åŃ£èĬĤ
    0.08
    Activations Density 0.023%

    No Known Activations