© 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. 14850
    Prev
    Next
    INDEX
    Explanations

    only

    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
    kar
    -0.10
    asso
    -0.09
    Typ
    -0.09
    ingt
    -0.09
     pleasantly
    -0.09
     typical
    -0.08
    thal
    -0.08
    alar
    -0.08
    cene
    -0.08
    uis
    -0.08
    POSITIVE LOGITS
     remaining
    0.23
     available
    0.21
     conceivable
    0.19
     thing
    0.19
     imaginable
    0.18
     viable
    0.18
     surviving
    0.17
     besides
    0.17
     Remaining
    0.16
    remaining
    0.16
    Activations Density 0.272%

    No Known Activations