© 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. 7794
    Prev
    Next
    INDEX
    Explanations

    asking for help or advice

    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
     Thankfully
    -0.12
     thankfully
    -0.12
    inde
    -0.11
    damn
    -0.11
     fortunately
    -0.11
     luckily
    -0.10
     undoubtedly
    -0.10
     Rene
    -0.10
    olec
    -0.10
     damn
    -0.10
    POSITIVE LOGITS
     perhaps
    0.28
     maybe
    0.27
     possibly
    0.21
    maybe
    0.21
     Perhaps
    0.20
    perhaps
    0.20
     Maybe
    0.19
    Perhaps
    0.18
     sometime
    0.17
    Maybe
    0.17
    Activations Density 0.061%

    No Known Activations