© 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. 47839
    Prev
    Next
    INDEX
    Explanations

    objective of this project

    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
    alten
    -0.11
     forfe
    -0.10
    atan
    -0.10
    lined
    -0.10
    claims
    -0.10
    /ion
    -0.10
    ubit
    -0.10
    erne
    -0.10
    çon
    -0.09
     Conditioning
    -0.09
    POSITIVE LOGITS
     Subject
    0.09
    kip
    0.09
    Subject
    0.08
    subject
    0.08
     Egg
    0.08
     subjective
    0.08
    reet
    0.08
    709
    0.08
     comp
    0.08
    ANGER
    0.08
    Activations Density 0.004%

    No Known Activations