© 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. 17315
    Prev
    Next
    INDEX
    Explanations

    http or https links

    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
     Peripheral
    -0.08
     imper
    -0.08
    lica
    -0.08
     cushion
    -0.07
    comed
    -0.07
     Disco
    -0.07
     undis
    -0.07
    eness
    -0.07
     Aero
    -0.07
    opia
    -0.07
    POSITIVE LOGITS
     Zucker
    0.12
    han
    0.11
     fatally
    0.11
     WTF
    0.11
    bolt
    0.11
     Byrne
    0.11
    .yy
    0.10
    <y
    0.10
    readonly
    0.10
     Valent
    0.10
    Activations Density 0.006%

    No Known Activations