© 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. 46358
    Prev
    Next
    INDEX
    Explanations

    å followed by special characters

    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
     Pee
    -0.11
    unes
    -0.09
    oa
    -0.09
    esper
    -0.09
     Stam
    -0.08
    elli
    -0.08
     Copies
    -0.08
    arkan
    -0.08
    uria
    -0.08
    rita
    -0.08
    POSITIVE LOGITS
     ver
    0.11
    imson
    0.10
    637
    0.10
    åĬŁ
    0.09
    pane
    0.09
     Tough
    0.09
     cir
    0.09
     backing
    0.09
     recl
    0.09
    izo
    0.09
    Activations Density 0.003%

    No Known Activations