© 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. 47122
    Prev
    Next
    INDEX
    Explanations

    with [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
     kak
    -0.11
     Palestine
    -0.10
     aprove
    -0.10
     securing
    -0.10
     McCart
    -0.10
    weis
    -0.10
    aben
    -0.10
    —he
    -0.10
    UED
    -0.10
    /ad
    -0.10
    POSITIVE LOGITS
    ought
    0.12
     ease
    0.12
     Ease
    0.11
     impunity
    0.11
     gusto
    0.11
    /of
    0.09
    ease
    0.08
     invisible
    0.08
    hin
    0.08
     abandon
    0.08
    Activations Density 0.344%

    No Known Activations