© 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. 34281
    Prev
    Next
    INDEX
    Explanations

    umbrella, patents, ear disease, Twitter feed

    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
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.08
    ereo
    -0.08
    entially
    -0.08
     orphan
    -0.08
    ONES
    -0.08
    âĵIJ
    -0.08
    OLER
    -0.08
    ÐIJÐĿ
    -0.08
    lest
    -0.08
     (?)
    -0.08
    POSITIVE LOGITS
    äºĮåŃĹ
    0.12
    داء
    0.08
    دار
    0.08
    omics
    0.08
    mailto
    0.08
    pheres
    0.08
    interopRequireDefault
    0.08
    ä¹ĭç¾İ
    0.08
    è¦ģéĹ»
    0.08
    -thirds
    0.08
    Activations Density 13.817%

    No Known Activations