© 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. 89201
    Prev
    Next
    INDEX
    Explanations

    SS followed by A, M, D, T

    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
    lea
    -0.09
     proceedings
    -0.08
     voyeur
    -0.08
     Vince
    -0.08
    .gf
    -0.08
     Scha
    -0.08
    lot
    -0.08
     Vinci
    -0.08
     WEST
    -0.08
    ussy
    -0.08
    POSITIVE LOGITS
    ous
    0.13
     Tube
    0.10
     tube
    0.10
     dint
    0.09
     Nach
    0.09
     Dil
    0.09
     undone
    0.09
    ando
    0.09
    /tr
    0.09
    antine
    0.08
    Activations Density 0.009%

    No Known Activations