© 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. 31498
    Prev
    Next
    INDEX
    Explanations

    unless you, absolutely need

    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
    lad
    -0.10
     ~>
    -0.10
    apan
    -0.10
    _FT
    -0.09
    urre
    -0.09
    lander
    -0.09
    enti
    -0.09
    unde
    -0.09
     Woodward
    -0.08
    nof
    -0.08
    POSITIVE LOGITS
     unavoidable
    0.42
     absolutely
    0.38
     unavoid
    0.32
     inevitable
    0.28
     necessity
    0.27
     Absolutely
    0.26
    Absolutely
    0.24
     insist
    0.23
     inev
    0.23
     insisted
    0.23
    Activations Density 0.156%

    No Known Activations