© 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. 92016
    Prev
    Next
    INDEX
    Explanations

    given something

    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
     pleasure
    -0.09
     shave
    -0.09
     Polic
    -0.09
     Shea
    -0.09
     Assistance
    -0.09
     Koch
    -0.09
     coz
    -0.08
    amen
    -0.08
     smoke
    -0.08
     rele
    -0.08
    POSITIVE LOGITS
     instructions
    0.19
     permission
    0.18
     directive
    0.14
     carte
    0.14
     ult
    0.14
     Instructions
    0.14
     guidelines
    0.14
     directives
    0.13
     orders
    0.13
     instruction
    0.13
    Activations Density 0.102%

    No Known Activations