© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31596
    Prev
    Next
    INDEX
    Explanations

    pine forests

    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
     cocoa
    -0.15
     Cocoa
    -0.13
     fruit
    -0.12
     chocol
    -0.11
    ocoa
    -0.11
     coc
    -0.10
     pand
    -0.10
     Soy
    -0.10
     Chocolate
    -0.10
     chocolate
    -0.10
    POSITIVE LOGITS
     Pine
    0.28
     pine
    0.28
    pine
    0.22
     needles
    0.21
     pineapple
    0.20
     cones
    0.20
     needle
    0.17
     cone
    0.17
     Cone
    0.17
    cone
    0.15
    Activations Density 0.391%

    No Known Activations