© 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. 31395
    Prev
    Next
    INDEX
    Explanations

    ABC or 123

    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
    peg
    -0.11
    IDL
    -0.09
     trouble
    -0.09
     blij
    -0.08
    {/*
    -0.08
    -ahead
    -0.08
    mdp
    -0.08
     WW
    -0.08
     confort
    -0.08
     noble
    -0.08
    POSITIVE LOGITS
    ABC
    0.15
     ABC
    0.15
    XYZ
    0.15
    abc
    0.15
    zy
    0.15
    xyz
    0.14
     abc
    0.13
    ZY
    0.13
    123
    0.13
     xyz
    0.13
    Activations Density 0.078%

    No Known Activations