© 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. 30496
    Prev
    Next
    INDEX
    Explanations

    However, exceptions, nevertheless

    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
     :(
    -0.15
     luckily
    -0.15
     fortunately
    -0.15
     Fortunately
    -0.15
    Fortunately
    -0.14
     Worse
    -0.13
     Luckily
    -0.13
    Luckily
    -0.12
     Thankfully
    -0.10
    fortunately
    -0.10
    POSITIVE LOGITS
     HOWEVER
    0.22
     Exceptions
    0.19
    However
    0.19
     exception
    0.18
     except
    0.18
    Nevertheless
    0.17
     however
    0.17
     nonetheless
    0.17
     nevertheless
    0.17
     Nevertheless
    0.17
    Activations Density 0.270%

    No Known Activations