© 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. 50027
    Prev
    Next
    INDEX
    Explanations

    looking for alternatives or information

    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
    oric
    -0.11
     Merr
    -0.11
     Moreno
    -0.11
     Morrison
    -0.11
    ìĭ
    -0.11
     reve
    -0.11
    -placement
    -0.11
    /Images
    -0.11
     Placement
    -0.11
    080
    -0.11
    POSITIVE LOGITS
     improvis
    0.23
     improv
    0.22
     borrow
    0.21
     borrowing
    0.21
     improvised
    0.20
     borrowed
    0.18
     Borrow
    0.17
     makeshift
    0.17
    borrow
    0.16
     rely
    0.15
    Activations Density 0.522%

    No Known Activations