© 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. 111965
    Prev
    Next
    INDEX
    Explanations

    listening for OK? hello

    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
     Associates
    -0.08
     invis
    -0.07
     Trent
    -0.07
     societal
    -0.07
     beaut
    -0.06
     beasts
    -0.06
    .tk
    -0.06
     hob
    -0.06
     Shadow
    -0.06
     Mant
    -0.06
    POSITIVE LOGITS
    otel
    0.12
     goose
    0.12
    -educated
    0.12
     Paging
    0.11
     jm
    0.11
    ắ
    0.11
     intercept
    0.11
    Interceptor
    0.11
    iff
    0.11
     intact
    0.11
    Activations Density 0.001%

    No Known Activations