© 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. 23524
    Prev
    Next
    INDEX
    Explanations

    animal-derived materials

    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
    åı¬åĽŀ
    -0.10
    询
    -0.10
    çİ»çĴĥ
    -0.09
    æľīæĦıæĢĿçļĦ
    -0.08
    夹
    -0.08
    åķĨçĶ¨è½¦
    -0.08
     sentinel
    -0.08
    å»ĭ
    -0.08
    磮
    -0.08
    åĦ¿å¥³
    -0.08
    POSITIVE LOGITS
    åĽ´
    0.10
    rie
    0.10
    aset
    0.09
    ì§Ī
    0.09
     cruelty
    0.09
    èĵij
    0.09
    å®ģæĦ¿
    0.09
    è£ĺ
    0.08
    é²ľè¡Ģ
    0.08
     animal
    0.08
    Activations Density 0.057%

    No Known Activations