© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113287
    Prev
    Next
    INDEX
    Explanations

    online services

    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
     online
    -0.10
    ardo
    -0.08
    odd
    -0.08
    online
    -0.08
     Online
    -0.07
     Claw
    -0.07
    cl
    -0.07
    isco
    -0.07
    ight
    -0.07
    ico
    -0.07
    POSITIVE LOGITS
     indeb
    0.13
    italic
    0.12
     Pont
    0.12
     banking
    0.12
    /on
    0.11
    -ahead
    0.11
     booking
    0.11
     predecess
    0.11
    ietf
    0.11
    /off
    0.11
    Activations Density 0.001%

    No Known Activations