© 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. 62711
    Prev
    Next
    INDEX
    Explanations

    DVD, CD, playable media

    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
    åħ«åŃĹ
    -0.09
    -twitter
    -0.09
    å¸IJ
    -0.08
    _draft
    -0.08
    æĶ¾å¼Ģ
    -0.08
    æĹ¥æĬ¥
    -0.08
    迷失
    -0.08
    -client
    -0.08
    ä½ļ
    -0.08
     Vulcan
    -0.08
    POSITIVE LOGITS
    ç¢Ł
    0.13
    DVD
    0.12
     CD
    0.11
     boxed
    0.10
     DVD
    0.10
    çĽĺ
    0.10
    _CD
    0.10
     CDs
    0.09
    åıijè¡Į
    0.09
     playable
    0.09
    Activations Density 0.074%

    No Known Activations