© 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. 15261
    Prev
    Next
    INDEX
    Explanations

    license or licencing terms

    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
    ower
    -0.12
    engo
    -0.12
     mate
    -0.10
    eting
    -0.10
     Germ
    -0.10
    edin
    -0.10
    Mate
    -0.10
    ingu
    -0.10
    oes
    -0.10
    osti
    -0.10
    POSITIVE LOGITS
     Ran
    0.10
    .gs
    0.08
     Dip
    0.07
    morph
    0.07
    izi
    0.07
     dated
    0.07
    754
    0.07
    ÌĢ
    0.07
    cff
    0.07
     disciplined
    0.07
    Activations Density 0.001%

    No Known Activations