© 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. 5213
    Prev
    Next
    INDEX
    Explanations

    strategy and security terms

    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
     distracting
    -0.09
     unanim
    -0.08
    etched
    -0.08
    astered
    -0.08
    urons
    -0.08
     halfway
    -0.08
    raq
    -0.08
     Quart
    -0.08
     hastily
    -0.08
     way
    -0.07
    POSITIVE LOGITS
     scenarios
    0.15
     techniques
    0.14
     situations
    0.13
     whereby
    0.13
     games
    0.13
     setups
    0.13
    -based
    0.13
    ionage
    0.12
     schemes
    0.12
     photography
    0.12
    Activations Density 0.123%

    No Known Activations