© 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. 46572
    Prev
    Next
    INDEX
    Explanations

    is a name ending

    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
    o
    -0.16
    e
    -0.16
    cu
    -0.14
    i
    -0.14
    h
    -0.13
    cus
    -0.13
    eel
    -0.12
    ionales
    -0.12
    ian
    -0.11
    cum
    -0.11
    POSITIVE LOGITS
    er
    0.17
    ed
    0.11
    ophage
    0.10
    ecake
    0.10
    ek
    0.09
    eker
    0.09
    oteric
    0.09
    ponse
    0.09
    ee
    0.09
    ey
    0.09
    Activations Density 0.094%

    No Known Activations