© 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. 117129
    Prev
    Next
    INDEX
    Explanations

    roman numerals and numbers

    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
     {*
    -0.12
     arrang
    -0.12
    ardon
    -0.11
     hops
    -0.11
     Corner
    -0.11
     horr
    -0.11
    _typeof
    -0.10
    asket
    -0.10
    _UNDEF
    -0.10
     enormously
    -0.10
    POSITIVE LOGITS
    xiv
    0.08
     iii
    0.08
     reb
    0.08
    iii
    0.08
     mut
    0.08
     iv
    0.08
     III
    0.08
     second
    0.08
    3
    0.08
     kil
    0.08
    Activations Density 0.297%

    No Known Activations