© 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. 50124
    Prev
    Next
    INDEX
    Explanations

    you want or choose

    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
    ovich
    -0.11
     thanking
    -0.09
    egg
    -0.09
    och
    -0.09
    esses
    -0.09
     Som
    -0.08
     Pett
    -0.08
    aters
    -0.08
     Lo
    -0.08
    ences
    -0.08
    POSITIVE LOGITS
     imaginable
    0.14
     deem
    0.13
     choose
    0.13
     imagine
    0.11
     chooses
    0.11
     dreamed
    0.11
     ever
    0.11
     EVER
    0.11
     imagination
    0.10
     conceivable
    0.10
    Activations Density 0.017%

    No Known Activations