© 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. 25348
    Prev
    Next
    INDEX
    Explanations

    up for / up and

    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
     Hatch
    -0.11
     Pos
    -0.10
    Localization
    -0.10
     krb
    -0.10
     Carrier
    -0.10
     overs
    -0.09
     Hick
    -0.09
     fin
    -0.09
     fingert
    -0.09
     clouds
    -0.09
    POSITIVE LOGITS
     tall
    0.15
     tallest
    0.12
     taller
    0.12
     straight
    0.10
     Tall
    0.09
     abruptly
    0.09
    reck
    0.09
    aday
    0.08
     stark
    0.08
    pone
    0.08
    Activations Density 0.002%

    No Known Activations