© 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. 89095
    Prev
    Next
    INDEX
    Explanations

    different forms or shapes

    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
    avage
    -0.10
    /cal
    -0.09
    INC
    -0.09
    /ext
    -0.09
    enario
    -0.09
    /fast
    -0.09
    ILT
    -0.09
    /free
    -0.09
    loh
    -0.09
    Undo
    -0.09
    POSITIVE LOGITS
    lessness
    0.15
    ulary
    0.15
    ulating
    0.14
    less
    0.13
    ality
    0.12
    lessly
    0.12
    atters
    0.11
    uala
    0.11
    ative
    0.11
    work
    0.10
    Activations Density 0.042%

    No Known Activations