© 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. 112987
    Prev
    Next
    INDEX
    Explanations

    cambridge or cam

    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
     Sail
    -0.10
     drain
    -0.10
     plat
    -0.10
     sailor
    -0.09
     drains
    -0.08
     PHI
    -0.08
     Eco
    -0.08
     saliva
    -0.08
     Sailor
    -0.08
    loi
    -0.08
    POSITIVE LOGITS
    (cam
    0.18
    Cam
    0.17
     cam
    0.16
    acam
    0.16
     Cam
    0.15
    .cam
    0.14
    cam
    0.14
    _cam
    0.13
    CAM
    0.13
    _CAM
    0.13
    Activations Density 0.193%

    No Known Activations