© 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. 26207
    Prev
    Next
    INDEX
    Explanations

    it followed by names or suffixes

    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
    is
    -0.16
    as
    -0.16
    on
    -0.16
    ation
    -0.13
    tings
    -0.13
    ted
    -0.12
    ary
    -0.12
    ta
    -0.12
    an
    -0.11
    asu
    -0.11
    POSITIVE LOGITS
    ers
    0.11
    adel
    0.11
     sustain
    0.10
     Microsystems
    0.10
    ICI
    0.10
    amins
    0.10
    Susan
    0.09
    nge
    0.09
    zen
    0.08
    usive
    0.08
    Activations Density 0.124%

    No Known Activations