© 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. 22420
    Prev
    Next
    INDEX
    Explanations

    web services, apps, and frameworks

    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
    noc
    -0.09
    asu
    -0.09
    身边çļĦ
    -0.09
    _website
    -0.09
    /testing
    -0.08
    yled
    -0.08
    污
    -0.08
    èĻı
    -0.08
    èĽ®
    -0.08
    rew
    -0.08
    POSITIVE LOGITS
    à¹Ħà¸ĭ
    0.12
    inars
    0.10
    dings
    0.10
    ght
    0.10
    纡
    0.10
    éģIJ
    0.10
    /web
    0.10
    èģĶ
    0.10
    nesday
    0.09
    -spinner
    0.09
    Activations Density 0.099%

    No Known Activations