© 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. 88068
    Prev
    Next
    INDEX
    Explanations

    colors and styles

    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
    ju
    -0.09
     Canc
    -0.09
    [out
    -0.09
    лиÑĨ
    -0.09
    .until
    -0.08
     Harden
    -0.08
    Reusable
    -0.08
     profund
    -0.08
     cho
    -0.08
    cken
    -0.08
    POSITIVE LOGITS
     yellow
    0.38
     blue
    0.37
     white
    0.37
     green
    0.36
     red
    0.36
     purple
    0.36
     black
    0.35
     brown
    0.34
     pink
    0.33
     orange
    0.33
    Activations Density 0.321%

    No Known Activations