© 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. 36183
    Prev
    Next
    INDEX
    Explanations

    version numbers

    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
    æı½
    -0.10
    éĩľ
    -0.09
    AAP
    -0.09
    oser
    -0.08
    å¹
    -0.08
    åı¬
    -0.08
    obb
    -0.08
    æ·ĭ
    -0.08
    enger
    -0.08
    osed
    -0.08
    POSITIVE LOGITS
    çīĪæľ¬
    0.12
     version
    0.11
    æ¶İ
    0.10
     sür
    0.10
    æľĢæĸ°
    0.10
    æľĢæĸ°çļĦ
    0.10
    /latest
    0.10
     versión
    0.09
     getVersion
    0.09
    ä¸ĢæľŁ
    0.09
    Activations Density 0.303%

    No Known Activations