© 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. 89750
    Prev
    Next
    INDEX
    Explanations

    run followed by 'je', 'escape', 'at', '-all', 'py', 'anga', or 'through'

    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
    ories
    -0.11
    una
    -0.09
     Ride
    -0.09
    AGON
    -0.09
     Pull
    -0.09
     Goodman
    -0.09
    267
    -0.09
    currency
    -0.09
    ities
    -0.09
    /right
    -0.09
    POSITIVE LOGITS
    ners
    0.19
    nings
    0.17
     rampant
    0.16
    nin
    0.15
    nable
    0.14
    away
    0.14
    aways
    0.14
     riot
    0.14
    escape
    0.13
    -through
    0.13
    Activations Density 0.105%

    No Known Activations