© 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. 47820
    Prev
    Next
    INDEX
    Explanations

    why questions

    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
     discrete
    -0.09
     pl
    -0.08
    zia
    -0.08
     Grandma
    -0.08
     pur
    -0.08
     tra
    -0.07
    .za
    -0.07
    Forge
    -0.07
     clo
    -0.07
    yan
    -0.07
    POSITIVE LOGITS
     suddenly
    0.13
    RL
    0.11
     absol
    0.11
     vanished
    0.11
    ssf
    0.11
     blink
    0.11
     Ideal
    0.11
     Nack
    0.10
     vibes
    0.10
    ãģ¾ãģŁ
    0.10
    Activations Density 0.034%

    No Known Activations