© 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. 31051
    Prev
    Next
    INDEX
    Explanations

    registered trademarks and logos

    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
    æĶ¹æŃ£
    -0.10
    ibia
    -0.10
    å¿«æĬ¥
    -0.08
    çŁ¥éģĵèĩªå·±
    -0.08
    èµ°å»Ĭ
    -0.08
    å¿ĥè¡Ģ
    -0.08
    çŃĭ
    -0.08
    edList
    -0.08
    æĹłæķĮ
    -0.08
    浩
    -0.08
    POSITIVE LOGITS
     logo
    0.16
    åķĨæłĩ
    0.15
    logo
    0.14
    .logo
    0.13
     Logo
    0.13
    Logo
    0.13
    /logo
    0.13
     logos
    0.12
    å¾½
    0.12
    æĭĽçīĮ
    0.11
    Activations Density 0.079%

    No Known Activations