© 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. 39035
    Prev
    Next
    INDEX
    Explanations

    Windows operating system versions

    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
    ties
    -0.10
    å·²ä¹ħçļĦ
    -0.10
    een
    -0.10
    ording
    -0.10
    tings
    -0.09
    åŃIJéĩĮ
    -0.09
    é²ľè¡Ģ
    -0.09
    ÑĤиÑĢов
    -0.09
    tle
    -0.09
    äºĨä¸Ģåı£
    -0.09
    POSITIVE LOGITS
    brew
    0.11
    /Linux
    0.09
    ìļĶ
    0.09
    Reserved
    0.09
    rewrite
    0.09
    âĦĹ
    0.08
     تعاÙĦÙī
    0.08
    -based
    0.08
    ัà¸Ķ
    0.08
    ifest
    0.08
    Activations Density 0.037%

    No Known Activations