© 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. 26208
    Prev
    Next
    INDEX
    Explanations

    form based

    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
    лÑĮ
    -0.12
     Stanton
    -0.11
    âĢ¦)
    -0.11
     )]↵
    -0.10
     Zuk
    -0.10
     'č↵
    -0.10
     Russ
    -0.10
    ,");↵
    -0.10
    олÑĮ
    -0.10
     ).↵↵
    -0.10
    POSITIVE LOGITS
    pid
    0.07
    hu
    0.07
    pop
    0.07
    ú
    0.07
    ´
    0.07
     reck
    0.07
    lt
    0.07
     Québec
    0.07
    em
    0.06
    chn
    0.06
    Activations Density 0.048%

    No Known Activations