© 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. 15168
    Prev
    Next
    INDEX
    Explanations

    Southeast

    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
     bust
    -0.09
    doch
    -0.08
     verd
    -0.08
    tical
    -0.08
    ulin
    -0.08
    okit
    -0.08
    обÑĭ
    -0.08
     flush
    -0.08
    *)(
    -0.08
    igh
    -0.08
    POSITIVE LOGITS
    venir
    0.17
    vl
    0.14
    theast
    0.12
    hait
    0.11
    lection
    0.11
    brane
    0.10
    Sou
    0.10
     sympath
    0.10
    /sp
    0.10
    straction
    0.10
    Activations Density 0.016%

    No Known Activations