© 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. 22636
    Prev
    Next
    INDEX
    Explanations

    DOPE, PE, Tope

    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
    IGN
    -0.09
    å±İ
    -0.09
    ulet
    -0.09
    ients
    -0.09
    ersed
    -0.09
    rog
    -0.08
    itch
    -0.08
    æĪijæīį
    -0.08
    ecess
    -0.08
    illac
    -0.08
    POSITIVE LOGITS
    icity
    0.10
    éļ§
    0.09
    ãĤ¹ãĤ¿
    0.09
    ouro
    0.09
    baz
    0.08
    -fi
    0.08
    ê¶Į
    0.08
    èĥ½ä½¿
    0.08
    lement
    0.08
    éĢł
    0.08
    Activations Density 0.014%

    No Known Activations