© 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. 8236
    Prev
    Next
    INDEX
    Explanations

    enter or input data

    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
    Ñĩем
    -0.10
    ouse
    -0.09
    andle
    -0.09
    taÅŁ
    -0.09
    æĺ¯éĿŀ
    -0.09
    ä¹İ
    -0.08
    èħł
    -0.08
    /header
    -0.08
    交ä»ĺ
    -0.08
    .documentation
    -0.08
    POSITIVE LOGITS
     into
    0.13
    è¿Ľåİ»
    0.12
    å½ķåħ¥
    0.11
    åºŃ
    0.10
    Into
    0.10
    ÑĢÑĥÑĩ
    0.10
    _into
    0.10
     vÃło
    0.09
     Into
    0.09
     INTO
    0.09
    Activations Density 0.092%

    No Known Activations