© 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. 15449
    Prev
    Next
    INDEX
    Explanations

    duke of

    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
    nah
    -0.10
     Shrine
    -0.09
    nage
    -0.09
    daq
    -0.08
    ning
    -0.08
    ymous
    -0.08
    nist
    -0.08
    -bin
    -0.08
    IPH
    -0.08
    nings
    -0.07
    POSITIVE LOGITS
    aroo
    0.11
    cea
    0.10
    hart
    0.10
    ë¡Ŀ
    0.10
    ãĤģ
    0.10
    leys
    0.09
    essa
    0.09
    peg
    0.09
     seminal
    0.09
    omm
    0.09
    Activations Density 0.018%

    No Known Activations