© 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. 7806
    Prev
    Next
    INDEX
    Explanations

    clearing land or vegetation

    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
    lav
    -0.11
    depth
    -0.11
     nearby
    -0.10
     Nearby
    -0.10
     depths
    -0.10
     hott
    -0.10
    igli
    -0.10
     Organic
    -0.10
     hiking
    -0.09
    eva
    -0.09
    POSITIVE LOGITS
     clearing
    0.35
     cleared
    0.31
     clearance
    0.24
     clears
    0.24
     Clear
    0.22
     clear
    0.19
    -clear
    0.19
     Clears
    0.19
     CLEAR
    0.18
    Clear
    0.18
    Activations Density 0.125%

    No Known Activations