© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36680
    Prev
    Next
    INDEX
    Explanations

    surname or part of name

    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
    樵
    -0.10
    åķ¡
    -0.09
    gy
    -0.09
    ieres
    -0.09
    angi
    -0.09
    çĬģ
    -0.09
    .usage
    -0.09
    åķıãģĦ
    -0.09
     gy
    -0.09
    tel
    -0.09
    POSITIVE LOGITS
    uren
    0.09
    缺
    0.09
    aling
    0.08
    è¤Ĭ
    0.08
    alm
    0.08
    buffer
    0.08
    aar
    0.08
    avan
    0.08
    /tab
    0.08
    amos
    0.08
    Activations Density 0.002%

    No Known Activations