© 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. 27621
    Prev
    Next
    INDEX
    Explanations

    post-traumatic, postoperative, post-colonoscopy

    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
    ãĥŃãĥ¼
    -0.11
    çŃĸ
    -0.10
    åħħè£ķ
    -0.10
    绶
    -0.09
    rador
    -0.09
    èĢķèĢĺ
    -0.09
    .mozilla
    -0.09
    /Instruction
    -0.09
    é«»
    -0.09
     Redemption
    -0.09
    POSITIVE LOGITS
    å¿ĥçIJĨ
    0.14
    æĬijéĥģ
    0.13
    æĥħ绪
    0.12
    å¿ĥçIJĨåģ¥åº·
    0.12
    çĦ¦èĻij
    0.11
    失èIJ½
    0.11
    æĥħç·Ĵ
    0.10
    èĩªåįij
    0.10
    çļĦå¿ĥçIJĨ
    0.10
     mental
    0.10
    Activations Density 0.111%

    No Known Activations