© 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. 23706
    Prev
    Next
    INDEX
    Explanations

    nie names and their following words

    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
    KIT
    -0.11
     dụng
    -0.10
    ç»ıæŁ¥
    -0.09
    管çIJĨå·¥ä½ľ
    -0.09
    GRAM
    -0.09
    vla
    -0.09
    ç®´
    -0.09
    æĪIJè´¥
    -0.09
    ÑĢей
    -0.08
    anon
    -0.08
    POSITIVE LOGITS
    ows
    0.09
     ones
    0.09
    åİ¿å§Ķ书记
    0.08
    ees
    0.08
    æ¿Ł
    0.08
    _-_
    0.08
    笳
    0.08
    TÄ°
    0.08
    åģļæ³ķ
    0.08
    ña
    0.08
    Activations Density 0.002%

    No Known Activations