© 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. 26997
    Prev
    Next
    INDEX
    Explanations

    or

    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
     ex
    -0.10
     noc
    -0.09
     inde
    -0.09
    lad
    -0.09
    pile
    -0.08
    rary
    -0.08
    upper
    -0.08
    _seg
    -0.08
    ableView
    -0.08
    ODO
    -0.08
    POSITIVE LOGITS
     Raised
    0.09
     Lionel
    0.09
    -nil
    0.08
    ktor
    0.08
    ouce
    0.08
    eses
    0.08
     Rag
    0.08
    ıs
    0.08
     Advertisement
    0.08
     Swe
    0.08
    Activations Density 0.023%

    No Known Activations