© 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. 26231
    Prev
    Next
    INDEX
    Explanations

    mountain related concepts

    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
     Cliff
    -0.14
     mound
    -0.14
     sands
    -0.14
     Prairie
    -0.13
     island
    -0.13
     Sands
    -0.12
     beach
    -0.12
     hill
    -0.12
     coastal
    -0.12
     Trafford
    -0.12
    POSITIVE LOGITS
     snow
    0.13
     ski
    0.13
     Snow
    0.12
    /high
    0.10
     Ski
    0.09
    snow
    0.09
     skiing
    0.09
    Snow
    0.09
    ī
    0.09
     passes
    0.09
    Activations Density 0.253%

    No Known Activations