© 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. 17832
    Prev
    Next
    INDEX
    Explanations

    numbers, codes, and identifiers

    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
    ingham
    -0.09
    ứ
    -0.09
    ussen
    -0.09
     signature
    -0.08
    etto
    -0.08
    ä¸
    -0.08
     Spec
    -0.08
     spec
    -0.08
     grin
    -0.08
     Swinger
    -0.08
    POSITIVE LOGITS
     Ol
    0.10
     Clo
    0.10
    bole
    0.10
    bor
    0.10
    XE
    0.09
    ÑĮÑİ
    0.09
     tys
    0.09
    iners
    0.09
     slashed
    0.09
    bo
    0.09
    Activations Density 0.002%

    No Known Activations