© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47427
    Prev
    Next
    INDEX
    Explanations

    Kam and Cam prefixes

    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
    Negative Logits
    ãĢħ
    -0.10
    ãĤĮ
    -0.10
    edReader
    -0.10
    archs
    -0.09
    gons
    -0.09
    gon
    -0.09
    ever
    -0.09
    orical
    -0.09
    à¹Į
    -0.09
    cco
    -0.09
    POSITIVE LOGITS
    éļ³
    0.13
    ouflage
    0.11
    eras
    0.09
    peg
    0.09
    ãĥ¬ãĤ¹
    0.09
    eroon
    0.09
    iku
    0.09
    uras
    0.09
    ulet
    0.09
    urate
    0.09
    Activations Density 0.072%

    No Known Activations