© 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. 53224
    Prev
    Next
    INDEX
    Explanations

    bogus or bogged down

    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
    lder
    -0.09
     Nä
    -0.09
    iten
    -0.09
    ipt
    -0.09
    sing
    -0.09
    ILLE
    -0.09
    angan
    -0.08
    aston
    -0.08
    dex
    -0.08
    飧æĢ§
    -0.08
    POSITIVE LOGITS
    busters
    0.10
    çĦ¶æĺ¯
    0.10
    erator
    0.10
    ified
    0.09
    หลวà¸ĩ
    0.09
    ä¼ļè§īå¾Ĺ
    0.09
    bies
    0.09
    0.09
    顸
    0.08
    olv
    0.08
    Activations Density 0.013%

    No Known Activations