© 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. 33700
    Prev
    Next
    INDEX
    Explanations

    compliance with license terms

    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
    stad
    -0.11
    .Pin
    -0.11
     Gomez
    -0.10
    egal
    -0.10
    orny
    -0.10
     âĨĴ↵↵
    -0.10
    urile
    -0.10
    Recovered
    -0.10
     humility
    -0.10
     Levine
    -0.10
    POSITIVE LOGITS
     Credits
    0.08
     afore
    0.08
    <'
    0.08
     vor
    0.08
    sv
    0.08
     FIG
    0.07
    rary
    0.07
     Org
    0.07
    854
    0.07
     belang
    0.07
    Activations Density 0.008%

    No Known Activations