© 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. 56483
    Prev
    Next
    INDEX
    Explanations

    sheep and related contexts

    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
    ä¸Ģè¶Ł
    -0.09
    ÑĩаÑĤ
    -0.09
    amp
    -0.09
    æĻ´
    -0.09
    icamente
    -0.09
    èĩªç§°
    -0.09
    ãĥ§ãĥ³
    -0.08
    èķī
    -0.08
    åİħ
    -0.08
    éĨī
    -0.08
    POSITIVE LOGITS
    ç¾Ķ
    0.11
     Hü
    0.10
    毳
    0.10
    驼
    0.09
     sheep
    0.09
    -haired
    0.09
    ç¥ľ
    0.09
    mans
    0.09
    dogs
    0.09
    åij¼åĴĮ
    0.09
    Activations Density 0.047%

    No Known Activations