© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46296
    Prev
    Next
    INDEX
    Explanations

    shame, ashamed, shameful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
        ↵    ↵
    -0.09
    ellers
    -0.09
    ics
    -0.09
    ий
    -0.08
    roman
    -0.08
    -minus
    -0.08
     harmless
    -0.08
    umm
    -0.08
    ignment
    -0.08
     style
    -0.08
    POSITIVE LOGITS
    fully
    0.29
    ful
    0.24
    lessly
    0.22
    fulness
    0.20
    full
    0.17
    less
    0.16
    lessness
    0.16
    FUL
    0.15
    FULL
    0.14
    fur
    0.13
    Activations Density 0.003%

    No Known Activations