© 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. 61425
    Prev
    Next
    INDEX
    Explanations

    Davidson and Parkinson

    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
    大æłij
    -0.11
    tings
    -0.10
    .synthetic
    -0.10
    amina
    -0.10
    eur
    -0.09
    累累
    -0.09
    osg
    -0.09
    imensional
    -0.09
    inel
    -0.09
    illac
    -0.09
    POSITIVE LOGITS
    0.10
    娥
    0.09
    åIJĮæŃ¥
    0.08
    åIJĦæĸ¹
    0.08
     Mitch
    0.08
    人éĢī
    0.08
    ör
    0.08
    anguard
    0.08
    ..\
    0.08
    åĪ°åľº
    0.08
    Activations Density 0.005%

    No Known Activations