© 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. 31121
    Prev
    Next
    INDEX
    Explanations

    up or down

    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
    yo
    -0.10
    iol
    -0.09
     lurking
    -0.09
    Horizontal
    -0.08
    aro
    -0.08
    mens
    -0.08
     Mens
    -0.08
    -level
    -0.08
     halo
    -0.08
    horizontal
    -0.08
    POSITIVE LOGITS
     stairs
    0.20
     hierarchy
    0.16
     hill
    0.16
     chimney
    0.15
     slopes
    0.15
     chute
    0.15
     avenue
    0.15
     ladder
    0.14
     staircase
    0.14
     slope
    0.14
    Activations Density 0.057%

    No Known Activations