© 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. 89785
    Prev
    Next
    INDEX
    Explanations

    search query

    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
     ceremon
    -0.13
    isode
    -0.11
    DataExchange
    -0.11
     meeting
    -0.11
    StateMachine
    -0.11
     Transition
    -0.11
    Communication
    -0.11
     protector
    -0.11
     meetings
    -0.10
    meeting
    -0.10
    POSITIVE LOGITS
     search
    0.49
     searches
    0.43
     Search
    0.39
     searching
    0.39
    -search
    0.36
    Search
    0.36
    search
    0.35
     Searches
    0.35
     searched
    0.34
     SEARCH
    0.34
    Activations Density 1.568%

    No Known Activations