© 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. 30698
    Prev
    Next
    INDEX
    Explanations

    critique, land, ninja, time, zone

    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
     literal
    -0.10
     nich
    -0.10
     lux
    -0.10
    ellig
    -0.09
     literally
    -0.09
    OLS
    -0.09
     Pare
    -0.09
     nave
    -0.09
     Ce
    -0.08
     sheer
    -0.08
    POSITIVE LOGITS
    âĦ¢
    0.22
    (tm
    0.19
    ©
    0.18
    ®
    0.16
    TM
    0.16
     syndrome
    0.15
     deluxe
    0.14
     ®
    0.14
     âĦ
    0.13
    (TM
    0.13
    Activations Density 0.130%

    No Known Activations