© 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. 116353
    Prev
    Next
    INDEX
    Explanations

    decided/shown/understand/assumes/seems not/that/how

    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
    ipe
    -0.11
     Fountain
    -0.10
    gee
    -0.10
    pedia
    -0.10
     whats
    -0.09
    ulong
    -0.09
     allegedly
    -0.09
     %"
    -0.09
    -0.09
    POOL
    -0.09
    POSITIVE LOGITS
     moreover
    0.14
     therefore
    0.12
     now
    0.12
     dim
    0.12
     again
    0.11
    ,
    0.11
     also
    0.11
     suddenly
    0.10
     vaguely
    0.10
    dim
    0.09
    Activations Density 0.092%

    No Known Activations