© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9204
    Prev
    Next
    INDEX
    Explanations

    subject to revision before publication

    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
    8
    -0.08
    2
    -0.08
    5
    -0.08
    enk
    -0.08
    4
    -0.08
    7
    -0.08
    ripe
    -0.08
    1
    -0.08
    smith
    -0.08
    lify
    -0.08
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.14
    å®ĮåĸĦ
    0.12
    ìĤ¬íķŃ
    0.12
    è¿ĩæĿ¥
    0.10
    bsp
    0.10
    Ñıз
    0.10
    IEWS
    0.10
    /update
    0.10
    STALL
    0.10
    ewing
    0.10
    Activations Density 0.015%

    No Known Activations