© 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. 31432
    Prev
    Next
    INDEX
    Explanations

    best games tends

    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
     Shel
    -0.11
     shel
    -0.10
     Blo
    -0.10
    hos
    -0.10
    inger
    -0.09
     Shelby
    -0.09
    ieber
    -0.09
    uckle
    -0.09
     Silicon
    -0.09
    dw
    -0.09
    POSITIVE LOGITS
    chy
    0.10
    ilst
    0.09
    pery
    0.09
     hang
    0.09
    Hang
    0.08
    acho
    0.08
    orris
    0.08
     dri
    0.08
    zem
    0.08
     hangs
    0.08
    Activations Density 0.090%

    No Known Activations