© 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. 19457
    Prev
    Next
    INDEX
    Explanations

    drying on paper towels

    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
    åīįä¸Ģ天
    -0.09
    è¡ĹåĮº
    -0.09
    é¡·
    -0.09
    ä¹ħ
    -0.08
    çĦĻ
    -0.08
    èµ·æĿ¥äºĨ
    -0.08
    veled
    -0.08
    atie
    -0.08
    åĵģä½į
    -0.08
    èµĦåĬ©
    -0.08
    POSITIVE LOGITS
     hal
    0.09
    èĩĬ
    0.09
    带ä¸Ĭ
    0.09
    å¹²
    0.08
    geh
    0.08
    æ¦Ĩ
    0.08
    _STRUCT
    0.08
    为客æĪ·
    0.08
    isl
    0.08
    illes
    0.08
    Activations Density 0.022%

    No Known Activations