© 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. 91777
    Prev
    Next
    INDEX
    Explanations

    U or U-related words

    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
     pom
    -0.09
    iver
    -0.08
    icl
    -0.08
    atoi
    -0.08
     stiff
    -0.08
     Titanic
    -0.08
     Foot
    -0.08
     disemb
    -0.07
     dac
    -0.07
    /jav
    -0.07
    POSITIVE LOGITS
    /U
    0.27
    (U
    0.27
     U
    0.26
    ,U
    0.23
    -U
    0.22
    .U
    0.22
    [U
    0.22
     UB
    0.21
     UA
    0.21
    <U
    0.20
    Activations Density 2.375%

    No Known Activations