© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48473
    Prev
    Next
    INDEX
    Explanations

    know what is happening

    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
     indeb
    -0.12
    raud
    -0.11
     Troll
    -0.11
    Authority
    -0.11
    ouro
    -0.11
    mux
    -0.11
     irresist
    -0.11
     Parkway
    -0.11
     hilar
    -0.11
    ugi
    -0.11
    POSITIVE LOGITS
     needs
    0.16
     pitfalls
    0.14
     expectations
    0.14
     requirements
    0.12
     Expect
    0.12
     capabilities
    0.12
     works
    0.11
     needed
    0.11
     expected
    0.11
     strengths
    0.11
    Activations Density 0.076%

    No Known Activations