© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50160
    Prev
    Next
    INDEX
    Explanations

    triggering events

    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
    æĦı大
    -0.10
    åįĩ
    -0.09
    访
    -0.09
    imus
    -0.09
    -NLS
    -0.09
    åģļèµ·
    -0.09
    exo
    -0.09
    çľ·
    -0.09
    åĵº
    -0.09
    çĿĢæīĭ
    -0.09
    POSITIVE LOGITS
    触åıij
    0.24
    trigger
    0.20
     trigger
    0.20
     triggers
    0.19
    Trigger
    0.18
     Trigger
    0.17
    _trigger
    0.17
    (trigger
    0.17
     triggering
    0.16
    .trigger
    0.16
    Activations Density 0.123%

    No Known Activations