© 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. 89081
    Prev
    Next
    INDEX
    Explanations

    depth and variations

    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
     spinner
    -0.09
    atron
    -0.08
     scram
    -0.08
     neigh
    -0.08
     sluggish
    -0.08
     gün
    -0.08
     unchecked
    -0.08
     whipping
    -0.08
    shr
    -0.08
    ASF
    -0.08
    POSITIVE LOGITS
     depth
    0.80
     depths
    0.73
     Depth
    0.71
     deep
    0.68
    depth
    0.66
     deeper
    0.65
    Depth
    0.64
     deepest
    0.63
    -depth
    0.61
     deepen
    0.60
    Activations Density 0.379%

    No Known Activations