© 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. 116683
    Prev
    Next
    INDEX
    Explanations

    rating scales and prediction

    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
    rit
    -0.10
    rita
    -0.10
    woods
    -0.10
    ries
    -0.10
    side
    -0.09
    Tit
    -0.09
    erton
    -0.09
    uns
    -0.09
    rid
    -0.09
    antly
    -0.09
    POSITIVE LOGITS
    payer
    0.17
     quo
    0.14
    ting
    0.12
     hikes
    0.10
    worthy
    0.10
    faction
    0.10
    inue
    0.10
    оÑĩ
    0.09
     hike
    0.09
    MUX
    0.09
    Activations Density 0.075%

    No Known Activations