© 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. 53584
    Prev
    Next
    INDEX
    Explanations

    reports sayings

    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
    èĭ±æīį
    -0.10
    åħĢ
    -0.10
    å¬ĸ
    -0.09
    å¾Ĥ
    -0.09
    åĽĽåŃ£
    -0.08
    åĽ½åĬ¡
    -0.08
    è¾ĥå¤ļ
    -0.08
    ield
    -0.08
    çľ·
    -0.08
    槲
    -0.08
    POSITIVE LOGITS
    è®°èĢħ
    0.09
    æħ¢æħ¢çļĦ
    0.09
    ä»Ĭ天æĪij们
    0.08
     hopeful
    0.08
    å°Ħ
    0.08
    rale
    0.08
     Pens
    0.08
    å¤ļ家
    0.08
    CBS
    0.08
     nud
    0.08
    Activations Density 0.166%

    No Known Activations