© 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. 39599
    Prev
    Next
    INDEX
    Explanations

    vin GREEN

    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
    å¸ļ
    -0.11
    ily
    -0.10
    illon
    -0.09
    è°®
    -0.09
    илÑĮ
    -0.09
    itution
    -0.09
    itone
    -0.08
    ülü
    -0.08
    .Raw
    -0.08
    .psi
    -0.08
    POSITIVE LOGITS
    èĩ³æѤ
    0.09
    aden
    0.09
    æĽ·
    0.09
    สหร
    0.08
    ster
    0.08
     Äijẳng
    0.08
     odom
    0.08
    åĩºèº«
    0.08
    arger
    0.08
     mutil
    0.08
    Activations Density 0.006%

    No Known Activations