© 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. 88074
    Prev
    Next
    INDEX
    Explanations

    copyright and license

    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
    loc
    -0.09
     Corps
    -0.09
     inland
    -0.08
    bolt
    -0.08
     LOC
    -0.08
     jung
    -0.08
    pector
    -0.08
     Loft
    -0.08
     inaugur
    -0.07
     outright
    -0.07
    POSITIVE LOGITS
    itta
    0.11
    oon
    0.11
     therein
    0.10
     elig
    0.10
    adesh
    0.10
    ETS
    0.10
    itia
    0.10
    SSI
    0.10
    nda
    0.10
    ledo
    0.10
    Activations Density 0.183%

    No Known Activations