© 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. 1425
    Prev
    Next
    INDEX
    Explanations

    hot weather and conditions

    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
    沧
    -0.09
    lev
    -0.09
    é«ĺçŃī
    -0.09
    èĩ³ä¸Ĭ
    -0.09
    lessly
    -0.09
    çľĭäºĨä¸Ģ
    -0.09
    座è°Ī
    -0.08
    çľĭä¸įæĩĤ
    -0.08
    ä½³
    -0.08
    RICS
    -0.08
    POSITIVE LOGITS
    lias
    0.10
    çĤĻ
    0.10
    èµ
    0.10
    asters
    0.09
     Gems
    0.09
    è´´
    0.09
    .inverse
    0.09
    itches
    0.08
    _VARS
    0.08
    å¸ĸ
    0.08
    Activations Density 0.174%

    No Known Activations