© 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. 3687
    Prev
    Next
    INDEX
    Explanations

    event or events indicating details

    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»
    -0.13
    ı
    -0.12
    ðŁı¼
    -0.11
    ðŁı½
    -0.10
    apter
    -0.10
    eren
    -0.09
    ptime
    -0.09
    lla
    -0.09
    TURE
    -0.09
    èĩ¾
    -0.09
    POSITIVE LOGITS
    uality
    0.19
    ually
    0.17
    uating
    0.12
    uate
    0.11
    uell
    0.11
    .ActionEvent
    0.10
    idue
    0.10
    nel
    0.10
    uated
    0.10
    ives
    0.10
    Activations Density 0.050%

    No Known Activations