© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60934
    Prev
    Next
    INDEX
    Explanations

    video game consoles and eras

    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
    æ°¸ä¹ħ
    -0.11
    ä¸įçIJĨ
    -0.10
    rait
    -0.10
    们çļĦ
    -0.09
    ZONE
    -0.09
    åĢij
    -0.09
    DCF
    -0.09
    åĬĽè¿ĺæĺ¯
    -0.08
    åıĺåĬ¨
    -0.08
    çĶ©
    -0.08
    POSITIVE LOGITS
    1
    0.08
    5
    0.08
    igh
    0.08
     Crowd
    0.08
    8
    0.08
    4
    0.08
    illion
    0.08
    ãģ»ãģĨ
    0.08
    6
    0.08
    3
    0.08
    Activations Density 0.018%

    No Known Activations