© 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. 11612
    Prev
    Next
    INDEX
    Explanations

    poet

    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
    ses
    -0.11
    sar
    -0.10
    sing
    -0.10
    ist
    -0.09
    si
    -0.09
    sync
    -0.09
    iente
    -0.09
    s
    -0.09
    sent
    -0.09
    ä¸¤åĽ½
    -0.09
    POSITIVE LOGITS
    ests
    0.11
    rix
    0.09
    esting
    0.09
    ç°ĭ
    0.09
    TING
    0.09
    est
    0.09
    ellt
    0.09
    0.09
    à¸ģรรม
    0.09
    _hal
    0.08
    Activations Density 0.011%

    No Known Activations