© 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. 4237
    Prev
    Next
    INDEX
    Explanations

    medical and research contexts

    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
     firing
    -0.09
     revel
    -0.08
     resign
    -0.08
     orthogonal
    -0.08
     pard
    -0.07
    owering
    -0.07
    oggle
    -0.07
    701
    -0.07
     bulb
    -0.07
     Axios
    -0.07
    POSITIVE LOGITS
    hausen
    0.11
     bufio
    0.11
     privile
    0.10
     tumble
    0.10
    ĻĤ
    0.10
     privilege
    0.10
     _$
    0.10
    ENTS
    0.09
     Battlefield
    0.09
     Lange
    0.09
    Activations Density 0.407%

    No Known Activations