© 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. 3254
    Prev
    Next
    INDEX
    Explanations

    excuses or reasons

    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
    æĺķ
    -0.09
    çĺ¾
    -0.09
     Schl
    -0.09
    enia
    -0.09
     Span
    -0.08
    .twitter
    -0.08
    ç¥ī
    -0.08
    åĸľåī§
    -0.08
     Covenant
    -0.08
    mia
    -0.08
    POSITIVE LOGITS
    åĢŁåı£
    0.31
    çIJĨçĶ±
    0.27
    çļĦçIJĨçĶ±
    0.25
     excuse
    0.24
     excuses
    0.22
     reasons
    0.18
     pretext
    0.18
    æIJª
    0.17
     ìĿ´ìľł
    0.15
     reason
    0.15
    Activations Density 0.064%

    No Known Activations