© 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. 91344
    Prev
    Next
    INDEX
    Explanations

    have a

    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
     abandonment
    -0.10
     extensively
    -0.09
    neys
    -0.09
    217
    -0.09
     slew
    -0.09
     promptly
    -0.09
     nada
    -0.09
     calam
    -0.09
     constituted
    -0.09
    (est
    -0.09
    POSITIVE LOGITS
     conversations
    0.12
     relationships
    0.11
    cov
    0.11
     Marino
    0.10
     separate
    0.09
    isd
    0.09
    /use
    0.09
     balanced
    0.09
     Carroll
    0.09
     conversation
    0.09
    Activations Density 0.272%

    No Known Activations