© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 88553
    Prev
    Next
    INDEX
    Explanations

    missing translations, news, variants

    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
     %.
    -0.10
    **,
    -0.10
    {},
    -0.10
    Liked
    -0.09
     "".
    -0.09
     ",
    -0.09
    },
    -0.09
    ",
    -0.08
    '',
    -0.08
     ,
    -0.08
    POSITIVE LOGITS
    ”çļĦ
    0.23
    "-
    0.14
    )section
    0.11
    -of
    0.10
    IFn
    0.10
    olson
    0.10
     rowspan
    0.10
    ()"
    0.10
     %-
    0.09
    %-
    0.09
    Activations Density 1.597%

    No Known Activations