© 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. 47198
    Prev
    Next
    INDEX
    Explanations

    method, process, or device

    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
     punching
    -0.10
     Indicator
    -0.09
     Emb
    -0.09
    utch
    -0.09
    wright
    -0.09
    289
    -0.09
     intervening
    -0.09
     unnecessarily
    -0.09
     thereafter
    -0.09
    emme
    -0.09
    POSITIVE LOGITS
     repeatedly
    0.19
     repet
    0.16
     continuously
    0.12
     until
    0.11
    WITHOUT
    0.11
     WHILE
    0.11
     sim
    0.10
     WITHOUT
    0.10
     upwards
    0.10
    .sim
    0.10
    Activations Density 0.165%

    No Known Activations