© 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. 112942
    Prev
    Next
    INDEX
    Explanations

    route or direction

    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
     kick
    -0.08
     kicking
    -0.08
     duly
    -0.08
     sho
    -0.08
     Kick
    -0.08
     floors
    -0.08
    floor
    -0.07
     Floor
    -0.07
     Intersection
    -0.07
     Nearby
    -0.07
    POSITIVE LOGITS
     kisses
    0.18
     saliva
    0.15
     across
    0.14
     havoc
    0.14
     sparing
    0.12
    nect
    0.12
    -routing
    0.12
     Across
    0.12
     misery
    0.12
     kissed
    0.12
    Activations Density 0.001%

    No Known Activations