© 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. 39338
    Prev
    Next
    INDEX
    Explanations

    background or context information

    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
    rais
    -0.09
    (contents
    -0.09
    大åŁİå¸Ĥ
    -0.08
    亡
    -0.08
    Verified
    -0.08
     Sty
    -0.08
    è·¨
    -0.08
    æĥĬ
    -0.08
    Routine
    -0.08
    UTC
    -0.08
    POSITIVE LOGITS
    èĥĮæĻ¯
    0.21
     context
    0.17
     background
    0.16
    çļĦåİĨåı²
    0.15
     Context
    0.14
     history
    0.14
    åİĨåı²
    0.14
    èĥĮæĻ¯ä¸ĭ
    0.14
    context
    0.14
    background
    0.13
    Activations Density 0.079%

    No Known Activations