© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46396
    Prev
    Next
    INDEX
    Explanations

    shamelessly, shamefully, sham, shame

    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
    zac
    -0.09
    uity
    -0.08
     conc
    -0.08
     succeeding
    -0.08
     appar
    -0.07
    stad
    -0.07
     succession
    -0.07
    853
    -0.07
    cao
    -0.07
    ellers
    -0.07
    POSITIVE LOGITS
    lessly
    0.26
     Shame
    0.21
    less
    0.21
     shame
    0.19
    fully
    0.18
    lessness
    0.16
    ful
    0.13
    LESS
    0.13
     sham
    0.13
     unab
    0.12
    Activations Density 0.004%

    No Known Activations