© 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. 112733
    Prev
    Next
    INDEX
    Explanations

    potential security risk ahead

    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
     Heard
    -0.09
     Lia
    -0.09
     clo
    -0.08
    rud
    -0.08
     fav
    -0.08
     dab
    -0.08
    —not
    -0.08
    Logical
    -0.08
     Couple
    -0.08
     sparing
    -0.08
    POSITIVE LOGITS
    uto
    0.11
    RAFT
    0.10
     Jas
    0.10
     Paula
    0.09
    /manual
    0.09
    empor
    0.09
    erin
    0.09
     Unsafe
    0.09
    uba
    0.09
    territ
    0.09
    Activations Density 0.001%

    No Known Activations