© 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. 35919
    Prev
    Next
    INDEX
    Explanations

    common sentence beginnings

    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
     “
    -0.12
    ottage
    -0.10
    “She
    -0.10
    åħ¨å¥Ĺ
    -0.09
    anium
    -0.09
    “I
    -0.09
    ãģĿãĤĮãģ«
    -0.09
    “The
    -0.09
    çļĦåĬŀæ³ķ
    -0.09
    “You
    -0.09
    POSITIVE LOGITS
    ä¹İ
    0.15
    1
    0.08
    ä¸ĭåİ»
    0.08
     dây
    0.08
    ded
    0.08
    çĪ·
    0.08
    çºĮ
    0.08
    0
    0.08
    å°ıæľĭåıĭ
    0.07
    -dist
    0.07
    Activations Density 0.082%

    No Known Activations