© 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. 11610
    Prev
    Next
    INDEX
    Explanations

    aliases

    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
    ened
    -0.10
    iable
    -0.10
    folk
    -0.09
    fully
    -0.09
    ening
    -0.09
    ĺ
    -0.09
    est
    -0.09
    ertype
    -0.08
    ady
    -0.08
    man
    -0.08
    POSITIVE LOGITS
    ../../../
    0.12
    elor
    0.10
    edList
    0.10
    管å§Ķä¼ļ
    0.10
    rst
    0.10
    éĢ£ãĤĮ
    0.10
    RIES
    0.09
    oses
    0.09
    ettes
    0.09
    ¡
    0.09
    Activations Density 0.377%

    No Known Activations