© 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. 2083
    Prev
    Next
    INDEX
    Explanations

    honor and recognition

    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
    å¼ĢæĿ¥
    -0.11
    sWith
    -0.11
    itive
    -0.11
    ye
    -0.11
    ãģĵãģ¨
    -0.10
    èĤļ
    -0.10
    sis
    -0.10
    voor
    -0.10
    adows
    -0.10
    orida
    -0.10
    POSITIVE LOGITS
    edList
    0.11
    fully
    0.11
    iginal
    0.11
    ful
    0.10
    thal
    0.10
    ë§ģ
    0.10
    ifice
    0.10
    ific
    0.10
    建åħļ
    0.10
    ably
    0.10
    Activations Density 0.018%

    No Known Activations