© 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. 91494
    Prev
    Next
    INDEX
    Explanations

    names following `q`, `ab`, `b`, `aw`, `ip`

    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
     carn
    -0.09
    -det
    -0.09
    utc
    -0.08
     sourced
    -0.08
     inner
    -0.08
    éĸĵ
    -0.08
    builtin
    -0.08
    idden
    -0.08
     Chanel
    -0.08
     damned
    -0.08
    POSITIVE LOGITS
    į°
    0.12
     unf
    0.12
    .SuppressLint
    0.10
     cheek
    0.09
    еÑģÑĤи
    0.09
     Wheeler
    0.08
    otros
    0.08
     cohorts
    0.08
    agua
    0.08
     bal
    0.08
    Activations Density 0.592%

    No Known Activations