© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 31137
    Prev
    Next
    INDEX
    Explanations

    go or go-

    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
     trouble
    -0.09
     dib
    -0.09
     visc
    -0.08
     toe
    -0.08
    olumn
    -0.08
    obs
    -0.08
     engr
    -0.08
     Toe
    -0.08
    stab
    -0.08
     Represent
    -0.08
    POSITIVE LOGITS
    /fwlink
    0.23
    Go
    0.14
     go
    0.13
     Go
    0.13
    .go
    0.12
    go
    0.12
    (go
    0.11
     goes
    0.11
     GO
    0.10
    -go
    0.10
    Activations Density 0.119%

    No Known Activations