© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 33408
    Prev
    Next
    INDEX
    Explanations

    Continue reading

    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
    KS
    -0.09
    ya
    -0.09
    ories
    -0.09
    fern
    -0.09
    Orm
    -0.09
    ks
    -0.09
    //*
    -0.09
    SMART
    -0.08
     Valent
    -0.08
     Morrow
    -0.08
    POSITIVE LOGITS
     below
    0.12
     Relatives
    0.10
     Below
    0.10
    lund
    0.09
    liest
    0.09
     Reading
    0.09
    Below
    0.09
     Beard
    0.09
     Snowden
    0.08
    esson
    0.08
    Activations Density 0.007%

    No Known Activations