© 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. 35105
    Prev
    Next
    INDEX
    Explanations

    price increases

    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
    ä¸ĭåįĬ
    -0.10
    KeyId
    -0.09
    rit
    -0.09
    à¸Ĭาย
    -0.09
    åĬłåĢį
    -0.08
     оÑĤкÑĢÑĭва
    -0.08
    é²»
    -0.08
    URN
    -0.08
    éĻIJãĤĬ
    -0.08
    scan
    -0.08
    POSITIVE LOGITS
    å¹ħ度
    0.15
    é¢IJ
    0.10
    /ref
    0.09
    áĢĴ
    0.09
    太快
    0.09
    åIJĪ
    0.09
    åIJİçļĦ
    0.08
    é¢ĸ
    0.08
     baud
    0.08
    以éĺ²
    0.08
    Activations Density 0.029%

    No Known Activations