© 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. 63033
    Prev
    Next
    INDEX
    Explanations

    legal terms, holidays, or wind

    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
    çĦ¦çĤ¹
    -0.12
    çĦ¦
    -0.11
    åѤ
    -0.10
     foc
    -0.09
    纯
    -0.09
    å½ĵæĻļ
    -0.08
    大èĥĨ
    -0.08
    ourd
    -0.08
    èĥĨ
    -0.08
    çģĮ
    -0.08
    POSITIVE LOGITS
    _subtype
    0.11
    pring
    0.09
    åģķ
    0.09
    ãģĦãģ¡
    0.09
     Blanc
    0.09
    å®ļæľŁ
    0.09
     sou
    0.09
    uds
    0.08
    ç°ª
    0.08
    ç°§
    0.08
    Activations Density 0.122%

    No Known Activations