© 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. 21470
    Prev
    Next
    INDEX
    Explanations

    fragment

    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
    iku
    -0.10
    thing
    -0.10
    /OR
    -0.10
    åºľ
    -0.09
    ses
    -0.09
    /from
    -0.09
    croft
    -0.09
    elo
    -0.08
    ancock
    -0.08
    edo
    -0.08
    POSITIVE LOGITS
    å©¿
    0.13
    agement
    0.11
    ustin
    0.10
    ção
    0.09
    rant
    0.09
    ол
    0.09
    tier
    0.09
     tá»ij
    0.09
    äºĨä¸įå°ij
    0.09
    (fragment
    0.09
    Activations Density 0.021%

    No Known Activations