© 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. 7993
    Prev
    Next
    INDEX
    Explanations

    junk

    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
    ðŁı»
    -0.10
    ogens
    -0.10
    迤
    -0.09
    eing
    -0.09
    ingle
    -0.09
    izo
    -0.09
    Ùĭ
    -0.09
    éĻ¢éķ¿
    -0.09
    åıijå±ķ缮æłĩ
    -0.09
    /mit
    -0.09
    POSITIVE LOGITS
    alytics
    0.12
    iest
    0.12
    iness
    0.11
    ified
    0.10
    ed
    0.10
    ers
    0.09
    athon
    0.09
    tion
    0.09
    ellaneous
    0.09
    tober
    0.09
    Activations Density 0.002%

    No Known Activations