© 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. 116543
    Prev
    Next
    INDEX
    Explanations

    both / and conjunctions

    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
     together
    -0.11
     hors
    -0.10
     Together
    -0.09
     semi
    -0.08
    hardt
    -0.08
    empl
    -0.08
     pair
    -0.08
     Mus
    -0.08
    fort
    -0.08
    inas
    -0.08
    POSITIVE LOGITS
     simultaneously
    0.27
     simultaneous
    0.25
    åIJĮæŶ
    0.23
     equally
    0.22
     simult
    0.22
     concurrently
    0.20
     alternating
    0.17
     dual
    0.15
     BOTH
    0.15
     Dual
    0.14
    Activations Density 1.470%

    No Known Activations