© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5516
    Prev
    Next
    INDEX
    Explanations

    away from

    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
    ouv
    -0.11
     sooner
    -0.10
    aben
    -0.09
    pcm
    -0.09
    /power
    -0.09
    à¸ģาร
    -0.09
     zar
    -0.09
     paving
    -0.09
     entitlement
    -0.08
    ObjectName
    -0.08
    POSITIVE LOGITS
    wards
    0.15
    ward
    0.12
     Tow
    0.11
     toward
    0.11
     towards
    0.11
    -facing
    0.10
     direction
    0.10
     directions
    0.10
     outward
    0.10
    stile
    0.10
    Activations Density 0.002%

    No Known Activations