© 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. 18100
    Prev
    Next
    INDEX
    Explanations

    safety and security

    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
     surviv
    -0.10
     shim
    -0.10
     coherent
    -0.10
     insecure
    -0.09
     secure
    -0.09
    osten
    -0.09
     dec
    -0.09
     associ
    -0.09
    secure
    -0.09
     XD
    -0.09
    POSITIVE LOGITS
     Dean
    0.09
    bac
    0.08
     Fet
    0.08
    &t
    0.08
     sterling
    0.08
    ida
    0.08
    ios
    0.08
     Naughty
    0.08
     tac
    0.08
    isoft
    0.08
    Activations Density 0.014%

    No Known Activations