© 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. 33340
    Prev
    Next
    INDEX
    Explanations

    found footage and surveillance 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
     Visibility
    -0.09
     photoc
    -0.09
     visibility
    -0.09
     photographers
    -0.09
     Photograph
    -0.08
     photographed
    -0.08
    phot
    -0.08
     chalk
    -0.08
    acier
    -0.08
    Phot
    -0.08
    POSITIVE LOGITS
     honeymoon
    0.13
     unsus
    0.12
     footage
    0.12
     captures
    0.11
     hidden
    0.11
     nanny
    0.11
     recordings
    0.11
     disguised
    0.11
     surv
    0.11
     capturing
    0.10
    Activations Density 0.008%

    No Known Activations