© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89791
    Prev
    Next
    INDEX
    Explanations

    os followed by ov or ki

    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
    lesh
    -0.10
    tml
    -0.10
    ÑĤе
    -0.10
    echa
    -0.09
     ocas
    -0.09
     substant
    -0.09
     rop
    -0.09
    tp
    -0.09
    tu
    -0.09
    ej
    -0.09
    POSITIVE LOGITS
    aurus
    0.19
    pora
    0.14
    se
    0.13
    sm
    0.12
    copy
    0.12
    hiba
    0.12
    hy
    0.12
     Angeles
    0.12
    so
    0.11
    mium
    0.11
    Activations Density 0.305%

    No Known Activations