© 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. 32318
    Prev
    Next
    INDEX
    Explanations

    Are you

    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
    igt
    -0.09
     actually
    -0.09
     literally
    -0.09
    ament
    -0.09
     Vel
    -0.09
    isha
    -0.09
    ilik
    -0.09
    utherland
    -0.09
    ima
    -0.09
     Pou
    -0.09
    POSITIVE LOGITS
     Ready
    0.16
    ready
    0.16
     ready
    0.15
     yet
    0.14
    -ready
    0.13
    Ready
    0.13
     READY
    0.12
    .ready
    0.11
     Yet
    0.10
    READY
    0.10
    Activations Density 0.057%

    No Known Activations