© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113807
    Prev
    Next
    INDEX
    Explanations

    performance, features, sensation

    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
    ché
    -0.10
     gib
    -0.10
    indh
    -0.10
    [in
    -0.10
     wherein
    -0.10
     tentative
    -0.10
     skew
    -0.10
    eller
    -0.10
     Dro
    -0.10
     Passage
    -0.09
    POSITIVE LOGITS
     courtesy
    0.13
     thanks
    0.12
     anywhere
    0.10
     Parsons
    0.10
     delivered
    0.09
     suitable
    0.09
     lasting
    0.09
     comparable
    0.09
     capable
    0.09
    Anywhere
    0.09
    Activations Density 0.048%

    No Known Activations