© 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. 30125
    Prev
    Next
    INDEX
    Explanations

    matter of

    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
    amus
    -0.07
     CPA
    -0.07
    atu
    -0.07
    jen
    -0.07
    atos
    -0.07
    ABLE
    -0.07
     suited
    -0.07
     eens
    -0.07
     unders
    -0.07
     Trap
    -0.07
    POSITIVE LOGITS
    fact
    0.13
     fact
    0.13
     matter
    0.13
    ongan
    0.12
     Fact
    0.12
     Overnight
    0.11
     deposits
    0.11
    matter
    0.11
    /material
    0.11
    enda
    0.11
    Activations Density 0.003%

    No Known Activations