© 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. 21853
    Prev
    Next
    INDEX
    Explanations

    Andy followed by a last name

    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
    ipt
    -0.12
    ends
    -0.10
    aub
    -0.09
    ight
    -0.09
    er
    -0.09
    kah
    -0.09
    aal
    -0.09
    æĸ¯é¡¿
    -0.09
    ened
    -0.08
    ic
    -0.08
    POSITIVE LOGITS
    ä¼ļåIJĮ
    0.10
    urations
    0.10
    tion
    0.10
    alysis
    0.09
    rollers
    0.09
    laus
    0.09
    nier
    0.09
    hev
    0.09
     sized
    0.09
    shore
    0.09
    Activations Density 0.007%

    No Known Activations