© 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. 17373
    Prev
    Next
    INDEX
    Explanations

    age of

    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
    ka
    -0.09
    ‘s
    -0.08
     sp
    -0.08
    idd
    -0.08
    iento
    -0.07
    -sp
    -0.07
    AE
    -0.07
    awa
    -0.07
     Riv
    -0.07
    481
    -0.07
    POSITIVE LOGITS
    wil
    0.12
     Wil
    0.10
     tandem
    0.10
     urn
    0.10
     wr
    0.10
    -reply
    0.09
     fraught
    0.09
     unt
    0.09
     rer
    0.09
     Rubio
    0.09
    Activations Density 0.271%

    No Known Activations