© 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. 15542
    Prev
    Next
    INDEX
    Explanations

    conjunctions or transitions

    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
    ADI
    -0.10
     Pep
    -0.09
    prising
    -0.09
    ropol
    -0.09
     Seems
    -0.09
     Patrol
    -0.08
    heim
    -0.08
    Gate
    -0.08
    tbl
    -0.08
    ãĤĮ
    -0.08
    POSITIVE LOGITS
     however
    0.18
    however
    0.15
     että
    0.13
     dass
    0.11
     że
    0.11
     that
    0.10
     "["
    0.10
     bahwa
    0.10
     že
    0.10
     therefore
    0.09
    Activations Density 0.140%

    No Known Activations