© 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. 6228
    Prev
    Next
    INDEX
    Explanations

    I have / I want / I need

    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
    iem
    -0.10
     there
    -0.10
     There
    -0.10
     paraph
    -0.10
    ICON
    -0.09
     multid
    -0.09
    there
    -0.09
     Greenwood
    -0.09
    spi
    -0.09
     Krish
    -0.09
    POSITIVE LOGITS
    illi
    0.12
     urgently
    0.11
     Mes
    0.10
    ku
    0.09
     need
    0.09
    agal
    0.09
    alus
    0.09
     needs
    0.09
    IFE
    0.09
     Ku
    0.09
    Activations Density 0.120%

    No Known Activations