© 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. 7874
    Prev
    Next
    INDEX
    Explanations

    "told this newspaper"

    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
    cest
    -0.12
    åIJij
    -0.11
    iffin
    -0.10
     Rif
    -0.10
     distilled
    -0.10
    åijĬ
    -0.09
     Cros
    -0.09
     ·
    -0.09
     ÑģообÑī
    -0.09
    .addTo
    -0.09
    POSITIVE LOGITS
     interviewer
    0.11
     Zig
    0.09
     Ib
    0.09
     commissioner
    0.09
     Moments
    0.09
    cke
    0.09
     turb
    0.09
     confessed
    0.09
     maxim
    0.09
     Confidential
    0.08
    Activations Density 0.166%

    No Known Activations