© 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. 50147
    Prev
    Next
    INDEX
    Explanations

    countries and regions

    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
    .rm
    -0.09
    æĤ¬å¿µ
    -0.09
    åĽ¢éķ¿
    -0.09
    åĬ£åĬ¿
    -0.09
    /she
    -0.09
    äºĽä»Ģä¹Ī
    -0.09
    对æѤ
    -0.09
    éĻIJ
    -0.08
    éĻ¤æѤä¹ĭå¤ĸ
    -0.08
    æĪ¿éĹ´éĩĮ
    -0.08
    POSITIVE LOGITS
    åıªæľī
    0.11
    ฯ
    0.11
    via
    0.11
    大éŨ
    0.11
    éĹ¨æ§Ľ
    0.10
    åıªä¸º
    0.10
     via
    0.10
    Via
    0.09
    èĪ¶
    0.09
    _via
    0.09
    Activations Density 0.157%

    No Known Activations