© 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. 54260
    Prev
    Next
    INDEX
    Explanations

    grand + common endings

    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
    sWith
    -0.10
    æĺ¥é£İ
    -0.09
    cker
    -0.09
    ãģ®ãģ¯
    -0.09
    åľŃ
    -0.08
    apor
    -0.08
    arian
    -0.08
    é»ij马
    -0.08
     cra
    -0.08
    .utf
    -0.08
    POSITIVE LOGITS
    eur
    0.11
    ously
    0.10
    ous
    0.10
    iously
    0.10
    iest
    0.09
    ize
    0.09
    eties
    0.09
    OUS
    0.09
    iosity
    0.09
    ly
    0.09
    Activations Density 0.004%

    No Known Activations