© 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. 25414
    Prev
    Next
    INDEX
    Explanations

    locations, countries, organization, people, music

    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
     cons
    -0.11
     pur
    -0.11
     goof
    -0.11
    veled
    -0.10
    /legal
    -0.10
     attendant
    -0.10
     permanently
    -0.10
     Pur
    -0.09
    dem
    -0.09
     recl
    -0.09
    POSITIVE LOGITS
     touches
    0.08
    -target
    0.08
    缮
    0.08
    hints
    0.08
     supported
    0.08
     Suit
    0.08
     RX
    0.08
    gard
    0.08
    RX
    0.07
    touches
    0.07
    Activations Density 0.001%

    No Known Activations