© 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. 91703
    Prev
    Next
    INDEX
    Explanations

    sometimes

    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
    527
    -0.10
    /rs
    -0.09
    uffer
    -0.09
    aine
    -0.09
    kir
    -0.09
    ooth
    -0.09
     eighty
    -0.09
    aire
    -0.08
    skins
    -0.08
     plat
    -0.08
    POSITIVE LOGITS
     occasionally
    0.26
     sometimes
    0.26
     periodically
    0.21
    sometimes
    0.20
     Occasionally
    0.20
     intermitt
    0.19
     Sometimes
    0.19
    Sometimes
    0.18
     often
    0.18
     frequently
    0.18
    Activations Density 0.014%

    No Known Activations