© 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. 25927
    Prev
    Next
    INDEX
    Explanations

    going up / upstairs

    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
    .fig
    -0.08
     "~
    -0.08
     Pivot
    -0.07
     Rig
    -0.07
     Bing
    -0.07
     stove
    -0.07
    PC
    -0.07
    KA
    -0.07
     Sto
    -0.07
     area
    -0.07
    POSITIVE LOGITS
     naar
    0.11
     toward
    0.11
    iode
    0.11
    à¸ĸ
    0.11
     sond
    0.11
    beb
    0.10
    /down
    0.10
     Ide
    0.10
    åĪ°
    0.10
     Ini
    0.10
    Activations Density 0.010%

    No Known Activations