© 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. 63145
    Prev
    Next
    INDEX
    Explanations

    decisions revoked or granted liberty

    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
    apore
    -0.09
    ä¸Ģäºĭ
    -0.09
    åĴĮåħ¶ä»ĸ
    -0.08
    çĹĺ
    -0.08
    åıĤ
    -0.08
    åĬŁ
    -0.08
    诣
    -0.08
    é«»
    -0.08
    åĬ¢
    -0.08
    vironment
    -0.08
    POSITIVE LOGITS
    è¿ĻèĪ¬
    0.09
    æ§Ń
    0.09
    borg
    0.09
    åĢĺèĭ¥
    0.09
    edly
    0.09
     Dollars
    0.09
    èĪ¬
    0.08
    æĽī
    0.08
    碰
    0.08
    æ¨¡æł·
    0.08
    Activations Density 0.711%

    No Known Activations