© 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. 112336
    Prev
    Next
    INDEX
    Explanations

    and connecting clauses

    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
     som
    -0.09
    _OT
    -0.09
     Rus
    -0.09
    Furthermore
    -0.08
     furthermore
    -0.08
    Or
    -0.08
    iat
    -0.08
    XA
    -0.08
    OA
    -0.08
    et
    -0.08
    POSITIVE LOGITS
    –and
    0.25
     And
    0.25
    —and
    0.24
    And
    0.22
    .And
    0.18
    â̦and
    0.18
    _and
    0.16
     luckily
    0.15
    _And
    0.14
    .and
    0.14
    Activations Density 0.644%

    No Known Activations