© 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. 15613
    Prev
    Next
    INDEX
    Explanations

    let followed by names or possessives

    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
    let
    -0.10
     let
    -0.10
    ity
    -0.10
    headline
    -0.10
    lep
    -0.09
    ERY
    -0.09
    ivel
    -0.09
    itti
    -0.09
    erty
    -0.09
     Kash
    -0.09
    POSITIVE LOGITS
    tings
    0.24
    ting
    0.22
    ters
    0.18
    tres
    0.18
    tered
    0.17
     us
    0.16
    term
    0.15
    ted
    0.14
    zte
    0.14
    ty
    0.14
    Activations Density 0.082%

    No Known Activations