© 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. 27681
    Prev
    Next
    INDEX
    Explanations

    role or function

    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
     phenomena
    -0.12
    ILLED
    -0.11
     wars
    -0.11
    RDD
    -0.11
     ende
    -0.10
     entities
    -0.10
     situation
    -0.10
    ogo
    -0.10
    ware
    -0.10
     functionalities
    -0.10
    POSITIVE LOGITS
    -than
    0.10
     unl
    0.10
     albeit
    0.10
     wartime
    0.09
     Farr
    0.09
     aforementioned
    0.09
     nighttime
    0.09
     undocumented
    0.08
     Greenwood
    0.08
     hypothetical
    0.07
    Activations Density 1.093%

    No Known Activations