© 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. 54421
    Prev
    Next
    INDEX
    Explanations

    obituary

    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
    åłĩ
    -0.10
    uxe
    -0.09
    èĦį
    -0.09
    ulan
    -0.09
    åĬ¨æīĭ
    -0.09
    ADIO
    -0.09
    宽容
    -0.09
    cape
    -0.09
    uggle
    -0.08
    说æĺİ书
    -0.08
    POSITIVE LOGITS
    миÑĢ
    0.09
     Friedrich
    0.09
    åĩłç§į
    0.09
    aire
    0.09
    ÑĢаж
    0.08
    亲åıĭ
    0.08
    潦
    0.08
    ç±į
    0.08
    -worthy
    0.08
    ÑĢажа
    0.08
    Activations Density 0.002%

    No Known Activations