© 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. 117188
    Prev
    Next
    INDEX
    Explanations

    upward direction

    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
     hands
    -0.11
     naked
    -0.09
     Hands
    -0.08
    ipur
    -0.08
     fingers
    -0.08
    aza
    -0.08
    atk
    -0.08
     Garr
    -0.08
     kept
    -0.07
    itz
    -0.07
    POSITIVE LOGITS
     Valle
    0.11
     Wat
    0.11
     valleys
    0.10
    /back
    0.10
     upward
    0.10
    /front
    0.10
    wat
    0.10
    -translate
    0.09
    /down
    0.09
     pans
    0.09
    Activations Density 0.008%

    No Known Activations