© 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. 50286
    Prev
    Next
    INDEX
    Explanations

    accept to leave

    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
     xxxx
    -0.11
     anatomy
    -0.09
     physiology
    -0.09
    icot
    -0.09
     nur
    -0.08
     Epid
    -0.08
     Anatomy
    -0.08
     IID
    -0.08
    urge
    -0.08
     Shaw
    -0.08
    POSITIVE LOGITS
    oki
    0.11
     Lazar
    0.10
    ooks
    0.10
     Mori
    0.09
     talents
    0.09
     such
    0.09
     partic
    0.09
     âľĵ
    0.09
     anyways
    0.09
    cli
    0.09
    Activations Density 0.051%

    No Known Activations