© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52809
    Prev
    Next
    INDEX
    Explanations

    add columns, directory, case, variables, array, values

    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
    éªĿ
    -0.10
    rtc
    -0.10
    æĶ¾å¼Ģ
    -0.10
    ieber
    -0.10
    åľ¨åĮĹ京
    -0.10
     fri
    -0.09
    æľĢéķ¿
    -0.09
    çīµ
    -0.08
    igue
    -0.08
    ä»ĬçĶŁ
    -0.08
    POSITIVE LOGITS
    ToList
    0.16
     Ø¥ÙĦÙĬÙĩا
    0.13
    ToArray
    0.12
    endum
    0.12
    icted
    0.12
    slashes
    0.11
    çłĿ
    0.11
     layer
    0.11
    ä¸Ĭåİ»
    0.11
    arty
    0.10
    Activations Density 0.280%

    No Known Activations