© 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. 89832
    Prev
    Next
    INDEX
    Explanations

    Presets, modes, settings

    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
     dangling
    -0.12
     sprung
    -0.11
     erect
    -0.11
     oversized
    -0.10
     unas
    -0.10
     sized
    -0.10
     Props
    -0.10
     plastic
    -0.10
     sizeof
    -0.10
    props
    -0.10
    POSITIVE LOGITS
     modes
    0.31
     mode
    0.28
     Modes
    0.25
     presets
    0.23
     Mode
    0.22
    modes
    0.22
    Modes
    0.22
     preset
    0.21
    _modes
    0.21
     settings
    0.21
    Activations Density 0.310%

    No Known Activations