© 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. 62105
    Prev
    Next
    INDEX
    Explanations

    suffix "-itis"

    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
    enco
    -0.10
    .mvp
    -0.10
    affen
    -0.09
    *****↵
    -0.09
    _lineno
    -0.09
    <small
    -0.08
    ÑģÑħод
    -0.08
    ARA
    -0.08
    çļĦç¼ĺ
    -0.08
     oci
    -0.08
    POSITIVE LOGITS
    ../../../
    0.14
    ium
    0.12
    ate
    0.11
    çĦ¶æĺ¯
    0.11
    ation
    0.11
    ere
    0.11
    ations
    0.10
    ments
    0.10
    ian
    0.10
    ifications
    0.10
    Activations Density 1.169%

    No Known Activations