© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6960
    Prev
    Next
    INDEX
    Explanations

    achievement and completion

    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
    éŀł
    -0.09
    ä¹İ
    -0.09
    æĮ¯
    -0.08
    .setHorizontal
    -0.08
    .setBorder
    -0.08
    ги
    -0.08
     nonatomic
    -0.08
     bordered
    -0.08
    å°¼äºļ
    -0.08
    /Area
    -0.08
    POSITIVE LOGITS
    è¯īæ±Ĥ
    0.12
    ä¸įäºĨ
    0.09
    upply
    0.09
    çIJīçĴĥ
    0.09
    ê¶ģ
    0.09
    æĬ±
    0.09
    çļĦ缮æłĩ
    0.09
    ãĤĴè¿İ
    0.09
    _goal
    0.09
    aux
    0.09
    Activations Density 0.112%

    No Known Activations