© 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. 56746
    Prev
    Next
    INDEX
    Explanations

    English word endings

    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
    éªĭ
    -0.11
    cul
    -0.11
    ãĤĵãģ§ãģĻãģijãģ©
    -0.09
    ä½ķåĨµ
    -0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.09
    ity
    -0.08
     اÙĦزÙħÙĨ
    -0.08
    leen
    -0.08
    izations
    -0.08
    andi
    -0.08
    POSITIVE LOGITS
    ertainment
    0.13
    elope
    0.12
    Åij
    0.11
    prises
    0.11
    esis
    0.10
    ninger
    0.10
    ourage
    0.10
    ding
    0.10
    ertia
    0.10
    rais
    0.10
    Activations Density 0.168%

    No Known Activations