© 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. 20908
    Prev
    Next
    INDEX
    Explanations

    Marshal badge or marshrutka

    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
    urate
    -0.11
    athers
    -0.09
    ä»İæľª
    -0.08
    ãģ¾ãģĻãģĮ
    -0.08
     starters
    -0.08
    ulous
    -0.08
    建档
    -0.08
    sWith
    -0.08
     Pearl
    -0.08
    inate
    -0.08
    POSITIVE LOGITS
    æ±ģ
    0.12
    stro
    0.10
     Ñģобой
    0.09
    欸
    0.09
    度
    0.09
    MOST
    0.09
    umbo
    0.08
     бÑĥдÑĥ
    0.08
    æĮº
    0.08
    ldr
    0.08
    Activations Density 0.006%

    No Known Activations