© 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. 50542
    Prev
    Next
    INDEX
    Explanations

    evil followed by entity or action

    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
    edly
    -0.10
    aal
    -0.10
    erc
    -0.09
    ilet
    -0.09
    es
    -0.08
    manship
    -0.08
    ingly
    -0.08
    iel
    -0.08
    APH
    -0.08
    esp
    -0.08
    POSITIVE LOGITS
    ution
    0.20
    -do
    0.18
     deeds
    0.16
     incarn
    0.15
    ness
    0.14
    -minded
    0.14
     genius
    0.14
     Genius
    0.13
    utions
    0.13
    icious
    0.13
    Activations Density 0.011%

    No Known Activations