© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19719
    Prev
    Next
    INDEX
    Explanations

    roles in plays and operas

    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
    asti
    -0.10
    çĿ¹
    -0.09
    arnation
    -0.09
    åĽ½åº¦
    -0.09
    ç¨Ģ
    -0.09
    mock
    -0.09
    沸èħ¾
    -0.09
    æĪIJæŀľ
    -0.09
    ledge
    -0.09
     Nurs
    -0.09
    POSITIVE LOGITS
    è§Ĵèī²
    0.10
    主è§Ĵ
    0.10
    enk
    0.09
    书æĪ¿
    0.09
    tero
    0.09
    ter
    0.08
    é£ŀè¡Įåijĺ
    0.08
     pil
    0.08
    abar
    0.08
    tering
    0.08
    Activations Density 0.111%

    No Known Activations