© 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. 6462
    Prev
    Next
    INDEX
    Explanations

    whenever always

    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
    ibu
    -0.11
     barring
    -0.10
     adherence
    -0.10
     refr
    -0.10
     vicious
    -0.09
    iren
    -0.09
    blr
    -0.09
    vault
    -0.09
    ATS
    -0.09
     Verd
    -0.09
    POSITIVE LOGITS
     whenever
    0.19
    Whenever
    0.17
     smile
    0.17
     everytime
    0.17
     Whenever
    0.17
     melt
    0.17
     always
    0.16
    always
    0.14
     soothing
    0.13
     uniquely
    0.13
    Activations Density 0.033%

    No Known Activations