© 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. 88158
    Prev
    Next
    INDEX
    Explanations

    ton of

    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
     gros
    -0.11
    tte
    -0.11
    tent
    -0.10
    orca
    -0.10
    hip
    -0.10
     darling
    -0.10
    iers
    -0.10
    lust
    -0.10
    eer
    -0.09
    t
    -0.09
    POSITIVE LOGITS
    nage
    0.12
    ne
    0.12
    neau
    0.12
    alamat
    0.10
    ights
    0.09
    asse
    0.09
     bricks
    0.09
    -ton
    0.09
    quil
    0.09
     ton
    0.08
    Activations Density 0.004%

    No Known Activations