© 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. 26764
    Prev
    Next
    INDEX
    Explanations

    places, shapes, occasion

    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
     compuls
    -0.14
     needy
    -0.14
     prost
    -0.13
     reluct
    -0.13
     clen
    -0.13
     mastur
    -0.13
     lawy
    -0.13
     personality
    -0.13
     undone
    -0.13
     embod
    -0.13
    POSITIVE LOGITS
     vegetation
    0.21
     buildings
    0.19
     debris
    0.19
     trees
    0.18
     visibility
    0.17
     rubble
    0.17
     wind
    0.16
     nearby
    0.16
     aerial
    0.16
     water
    0.16
    Activations Density 0.688%

    No Known Activations