© 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. 26509
    Prev
    Next
    INDEX
    Explanations

    names ending in -son, -ta, -tte, -du, -sey, -nna

    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
    athan
    -0.07
     Sachs
    -0.07
    WS
    -0.07
     Bauer
    -0.07
     Everywhere
    -0.07
    gens
    -0.07
    -
    -0.07
     paw
    -0.07
     Licht
    -0.07
     elastic
    -0.06
    POSITIVE LOGITS
     Entertainment
    0.11
    forme
    0.10
     Films
    0.10
    "},"
    0.09
    tty
    0.09
    dera
    0.09
    imps
    0.09
    ijd
    0.09
     regress
    0.09
    ewan
    0.09
    Activations Density 0.427%

    No Known Activations