© 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. 92134
    Prev
    Next
    INDEX
    Explanations

    origin or 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
     Located
    -0.14
    eor
    -0.12
     located
    -0.12
    located
    -0.11
    Located
    -0.11
     populous
    -0.11
    ÙĪد
    -0.10
    -mf
    -0.10
     situated
    -0.10
     moveTo
    -0.10
    POSITIVE LOGITS
     elsewhere
    0.22
     below
    0.21
     outside
    0.21
     somewhere
    0.21
     inside
    0.20
     abroad
    0.19
     afar
    0.19
     beyond
    0.18
     above
    0.16
     outdoors
    0.16
    Activations Density 0.114%

    No Known Activations