© 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. 37235
    Prev
    Next
    INDEX
    Explanations

    years in prison

    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
    ipes
    -0.10
    0
    -0.09
    9
    -0.08
    8
    -0.08
    pir
    -0.08
     Linda
    -0.08
     tort
    -0.08
    éĻį
    -0.08
     lap
    -0.08
    3
    -0.08
    POSITIVE LOGITS
    èĢ½
    0.10
    æĻļå¹´
    0.09
    æĿŁ
    0.09
    MENT
    0.09
    æĢ¡
    0.09
    .baidu
    0.09
    以åĨħ
    0.08
     Canter
    0.08
    uler
    0.08
    鼶éĥ¨ä»¶
    0.08
    Activations Density 0.014%

    No Known Activations