© 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. 50116
    Prev
    Next
    INDEX
    Explanations

    endings / conclusions

    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
     Continuing
    -0.13
    Immediately
    -0.11
     immediately
    -0.11
     Currently
    -0.11
    Contin
    -0.11
     continue
    -0.11
    continued
    -0.11
     continuing
    -0.10
     later
    -0.10
     continued
    -0.10
    POSITIVE LOGITS
     enjoyed
    0.16
     throughout
    0.16
    Throughout
    0.15
     Throughout
    0.14
     goodbye
    0.13
     farewell
    0.12
     enjoyable
    0.12
     journey
    0.11
    ãģĤãĤĬãģĮãģ¨ãģĨãģĶãģĸ
    0.10
     bye
    0.10
    Activations Density 0.261%

    No Known Activations