© 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. 36999
    Prev
    Next
    INDEX
    Explanations

    incrementing count or sequence

    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
     Permanent
    -0.08
    eut
    -0.08
    æ²īæ·Ģ
    -0.08
    å·§åIJĪ
    -0.08
    eri
    -0.08
    åİĭå®ŀ
    -0.08
     permanent
    -0.08
    thermal
    -0.08
    æĢ¯
    -0.08
    å¤ĩ
    -0.08
    POSITIVE LOGITS
     range
    0.12
    .range
    0.11
    循
    0.11
    缴åĪ°
    0.11
    循çݯ
    0.11
    èĮĥåĽ´
    0.10
    _range
    0.10
    (range
    0.10
    range
    0.10
    缴èĩ³
    0.10
    Activations Density 0.456%

    No Known Activations