© 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. 47551
    Prev
    Next
    INDEX
    Explanations

    game or item status

    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
     Jog
    -0.07
     unknown
    -0.07
    /how
    -0.07
    lot
    -0.07
     Scri
    -0.07
    imple
    -0.07
    .fx
    -0.07
     Sey
    -0.07
    aki
    -0.07
     bite
    -0.07
    POSITIVE LOGITS
    iew
    0.12
    !!,
    0.11
    haar
    0.11
    ìŀĦ
    0.11
    urgent
    0.10
    .cf
    0.10
    =true
    0.10
    oppel
    0.10
     flag
    0.10
     Knox
    0.10
    Activations Density 0.608%

    No Known Activations