© 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. 7674
    Prev
    Next
    INDEX
    Explanations

    hourly ending with 1

    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
    ãĥ¼ãĥī
    -0.11
    ider
    -0.11
     Semester
    -0.10
     splash
    -0.10
    esson
    -0.10
    unu
    -0.10
    owy
    -0.09
    CastException
    -0.09
    prung
    -0.09
    _singleton
    -0.09
    POSITIVE LOGITS
     visceral
    0.08
    sville
    0.08
    tc
    0.08
    tx
    0.08
     caring
    0.08
     premature
    0.08
     Ku
    0.08
     chauff
    0.08
    traffic
    0.08
     mt
    0.07
    Activations Density 0.001%

    No Known Activations