© 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. 15751
    Prev
    Next
    INDEX
    Explanations

    edge or edges

    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
    ater
    -0.10
     hor
    -0.10
    canf
    -0.08
    ures
    -0.08
     tentative
    -0.08
     McConnell
    -0.08
     disposed
    -0.08
    iners
    -0.08
    tent
    -0.08
     Hans
    -0.08
    POSITIVE LOGITS
    combe
    0.15
     sharpen
    0.12
    -edge
    0.11
     raz
    0.11
    _SU
    0.10
    cliffe
    0.10
    ledge
    0.10
    lett
    0.10
     Razor
    0.10
    ITT
    0.10
    Activations Density 0.028%

    No Known Activations