© 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. 34954
    Prev
    Next
    INDEX
    Explanations

    mountain associated place names

    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
     rÃłng
    -0.11
    ë¥ł
    -0.10
    enstein
    -0.10
    vious
    -0.10
    ctors
    -0.10
    ·æĸ°
    -0.09
    念头
    -0.09
    gers
    -0.09
    Ùij
    -0.09
    uch
    -0.09
    POSITIVE LOGITS
    æ¥Ĥ
    0.10
    alsa
    0.10
    ized
    0.10
    astic
    0.10
    maj
    0.10
    lijk
    0.09
    bike
    0.09
    croft
    0.09
    IZER
    0.09
    ry
    0.09
    Activations Density 0.022%

    No Known Activations