© 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. 29852
    Prev
    Next
    INDEX
    Explanations

    ik, iki, ker

    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
    Hur
    -0.11
     Humb
    -0.10
    /spec
    -0.10
     McB
    -0.10
     Holl
    -0.10
    AMED
    -0.10
     Cout
    -0.10
    alli
    -0.10
     churn
    -0.10
     bright
    -0.10
    POSITIVE LOGITS
    eda
    0.11
    uno
    0.10
    peng
    0.09
    hti
    0.08
    inci
    0.08
    isoft
    0.08
    thy
    0.08
    ether
    0.08
     longer
    0.07
     boot
    0.07
    Activations Density 0.036%

    No Known Activations