© 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. 15504
    Prev
    Next
    INDEX
    Explanations

    limited to

    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
     Daly
    -0.10
    -Smith
    -0.10
     palms
    -0.09
     beyond
    -0.08
     Kom
    -0.08
    rar
    -0.08
     Rosenberg
    -0.08
     Kai
    -0.08
     liter
    -0.08
    arella
    -0.08
    POSITIVE LOGITS
     itself
    0.46
    -only
    0.22
     themselves
    0.21
     only
    0.21
     herself
    0.20
    _only
    0.19
    Only
    0.19
    only
    0.19
     Only
    0.18
     ONLY
    0.18
    Activations Density 0.262%

    No Known Activations