© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 113113
    Prev
    Next
    INDEX
    Explanations

    .but and so

    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
     however
    -0.14
    /OR
    -0.11
     HOWEVER
    -0.11
    however
    -0.11
     plains
    -0.10
     jedoch
    -0.10
     furthermore
    -0.10
     Rochester
    -0.09
    emarks
    -0.09
     Cue
    -0.09
    POSITIVE LOGITS
    .But
    0.27
     But
    0.27
    But
    0.25
     And
    0.22
    And
    0.19
    .And
    0.18
    _And
    0.11
     So
    0.11
     butt
    0.11
    .but
    0.10
    Activations Density 0.154%

    No Known Activations