© 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. 114380
    Prev
    Next
    INDEX
    Explanations

    photography and cameras

    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
    айд
    -0.11
     frec
    -0.10
    drink
    -0.10
    /board
    -0.10
    PEAR
    -0.09
     responder
    -0.09
     mech
    -0.09
     ember
    -0.09
     Tavern
    -0.09
     breakout
    -0.09
    POSITIVE LOGITS
     camera
    0.49
     photography
    0.46
     photographer
    0.45
     cameras
    0.45
     photographers
    0.44
     Camera
    0.44
     Photography
    0.43
     camer
    0.41
     photographic
    0.41
     filming
    0.41
    Activations Density 0.515%

    No Known Activations