© 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. 30967
    Prev
    Next
    INDEX
    Explanations

    & followed by word

    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
    管çIJĨåĴĮ
    -0.12
     anda
    -0.09
     вÑĭп
    -0.09
    ç»ĻäºĪäºĨ
    -0.08
     Revel
    -0.08
    åĸŁ
    -0.08
    æľĢ大çļĦ
    -0.08
     acquaintance
    -0.08
    çIJĨ解åĴĮ
    -0.08
    ×ķ׾×Ŀ
    -0.08
    POSITIVE LOGITS
    amp
    0.27
    raquo
    0.14
     amp
    0.14
    AMP
    0.13
    nbsp
    0.13
    amps
    0.12
    emsp
    0.12
    apos
    0.11
    quot
    0.11
    èħĪ
    0.10
    Activations Density 0.030%

    No Known Activations