© 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. 90837
    Prev
    Next
    INDEX
    Explanations

    un-, undo, unwind, unfold, unfinished, undefined

    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
    s
    -0.12
    ALLY
    -0.12
    umar
    -0.11
    dpi
    -0.11
    aley
    -0.11
    odore
    -0.10
    tsy
    -0.10
    agon
    -0.10
     Nach
    -0.10
    ала
    -0.10
    POSITIVE LOGITS
     cin
    0.09
    pez
    0.09
    ÑģÑĤв
    0.09
    heit
    0.08
    ÑĪ
    0.08
    /disable
    0.07
    ibil
    0.07
    lear
    0.07
    /reset
    0.07
    ño
    0.07
    Activations Density 0.005%

    No Known Activations