© 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. 7419
    Prev
    Next
    INDEX
    Explanations

    technical concepts and processes

    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
     JAN
    -0.09
     Bernstein
    -0.09
    La
    -0.09
     Hastings
    -0.09
    ulk
    -0.09
    lest
    -0.09
     rem
    -0.08
    .cond
    -0.08
    rale
    -0.08
    rost
    -0.08
    POSITIVE LOGITS
    elf
    0.11
     itself
    0.11
     Dub
    0.09
     Duck
    0.09
    AN
    0.08
     bloom
    0.08
    ene
    0.08
     Carroll
    0.08
    eref
    0.08
    orama
    0.08
    Activations Density 3.006%

    No Known Activations