© 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. 3831
    Prev
    Next
    INDEX
    Explanations

    corn, agent, anatomy

    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
    æĤ¦
    -0.12
    交æµģåIJĪä½ľ
    -0.09
    å¢ĥ
    -0.08
    åĬĪ
    -0.08
     repaint
    -0.08
    åĨ¢
    -0.08
    æłī
    -0.08
    绪
    -0.08
    ücken
    -0.08
    åľ°ä¸Ń
    -0.08
    POSITIVE LOGITS
    æ·Ģç²ī
    0.10
    æ²¥
    0.10
    课åłĤ
    0.10
    -flash
    0.09
    å°ĸåı«
    0.09
    upo
    0.09
    IEL
    0.09
    flo
    0.09
    åĽĽå¤Ħ
    0.09
    èĶĵ
    0.09
    Activations Density 0.045%

    No Known Activations