© 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. 116184
    Prev
    Next
    INDEX
    Explanations

    first, next, or second sequence

    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
    eli
    -0.10
     entirety
    -0.09
    cede
    -0.09
    uce
    -0.09
    ieu
    -0.08
    /lg
    -0.08
     Rede
    -0.08
    acja
    -0.08
     Gone
    -0.08
     pane
    -0.08
    POSITIVE LOGITS
     dib
    0.13
    arily
    0.11
     honors
    0.11
     Vit
    0.11
    ially
    0.11
     hon
    0.10
    tier
    0.10
    chang
    0.09
    ablish
    0.09
     Su
    0.09
    Activations Density 0.075%

    No Known Activations