© 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. 31350
    Prev
    Next
    INDEX
    Explanations

    Kel followed by logg or LY

    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
    ########
    -0.11
     convention
    -0.10
     Carolina
    -0.09
    elay
    -0.09
     Cata
    -0.09
    geh
    -0.09
     truthful
    -0.08
     acute
    -0.08
     Fired
    -0.08
     recount
    -0.08
    POSITIVE LOGITS
    logg
    0.16
    lyph
    0.12
    OpenHelper
    0.10
    logs
    0.09
    VIN
    0.09
    IRT
    0.09
    OrCreate
    0.09
    FAST
    0.09
    wner
    0.09
    LY
    0.09
    Activations Density 0.061%

    No Known Activations