© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16007
    Prev
    Next
    INDEX
    Explanations

    view, perspective, vistas

    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
     sounding
    -0.11
    ascript
    -0.11
     whispers
    -0.10
     tones
    -0.10
     touched
    -0.10
     Weiner
    -0.10
     Clone
    -0.09
    Clone
    -0.09
     whisper
    -0.09
     sensed
    -0.09
    POSITIVE LOGITS
     view
    0.24
     views
    0.21
     perspective
    0.20
     View
    0.19
     perspectives
    0.18
     viewpoint
    0.17
     panoramic
    0.17
    View
    0.16
    view
    0.16
     vistas
    0.16
    Activations Density 0.087%

    No Known Activations