© 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. 116934
    Prev
    Next
    INDEX
    Explanations

    a/an/another before a noun

    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
    emu
    -0.11
    Ticker
    -0.10
    ape
    -0.10
    kee
    -0.09
    imit
    -0.09
     popping
    -0.09
    aba
    -0.09
    asu
    -0.09
     Satan
    -0.09
     popped
    -0.09
    POSITIVE LOGITS
     coma
    0.18
     frenzy
    0.17
     trance
    0.14
     state
    0.14
     position
    0.12
    coma
    0.12
     sembl
    0.11
     spree
    0.11
     vortex
    0.11
     stup
    0.11
    Activations Density 0.058%

    No Known Activations