© 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. 32203
    Prev
    Next
    INDEX
    Explanations

    boundaries or restrictions

    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
    éĽī
    -0.10
    é«ĺçļĦ
    -0.10
    ç¬ı
    -0.10
    ä¸įè´Ł
    -0.09
    åħī彩
    -0.09
    .MSG
    -0.09
    vore
    -0.09
    æī£
    -0.09
    æ·¡åĮĸ
    -0.09
    桶
    -0.09
    POSITIVE LOGITS
     limits
    0.18
    çķĮéĻIJ
    0.17
    éĻIJ度
    0.17
    æŀģéĻIJ
    0.16
     Limits
    0.15
    éĻIJ
    0.15
    Limits
    0.14
    limits
    0.14
     Limit
    0.13
    éĻIJé¢Ŀ
    0.13
    Activations Density 0.046%

    No Known Activations