© 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. 91340
    Prev
    Next
    INDEX
    Explanations

    concessive 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
     And
    -0.29
    And
    -0.28
    ,and
    -0.28
    ï¼Įå¹¶
    -0.25
    â̦and
    -0.25
    .And
    -0.20
    —and
    -0.19
    –and
    -0.18
    )&&
    -0.17
    .and
    -0.17
    POSITIVE LOGITS
     albeit
    0.14
     despite
    0.14
     lest
    0.13
    lest
    0.13
     whilst
    0.12
     while
    0.12
     except
    0.11
     unless
    0.11
     although
    0.11
    ))/(
    0.11
    Activations Density 1.716%

    No Known Activations