© 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. 61917
    Prev
    Next
    INDEX
    Explanations

    blue light

    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
     tats
    -0.10
    ä¸Ģä½ĵ
    -0.10
    imson
    -0.09
    çĬ¬
    -0.09
    utz
    -0.09
    欢
    -0.09
     Redistributions
    -0.09
     ENT
    -0.09
    åĬ£
    -0.08
    awy
    -0.08
    POSITIVE LOGITS
    èĵĿ
    0.14
    èĹį
    0.12
     Blue
    0.11
    blue
    0.11
    _blue
    0.11
    -blue
    0.11
     blue
    0.11
    Blue
    0.10
    èĵĿèī²
    0.10
    /blue
    0.10
    Activations Density 0.060%

    No Known Activations