© 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. 26775
    Prev
    Next
    INDEX
    Explanations

    adjectives describing extremes or strong qualities

    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
    ’s
    -0.10
    's
    -0.09
     the
    -0.09
     resembling
    -0.07
     that
    -0.07
     in
    -0.07
     with
    -0.07
    aran
    -0.06
    tern
    -0.06
     for
    -0.06
    POSITIVE LOGITS
     confines
    0.23
     entirety
    0.21
     nature
    0.20
    ness
    0.19
     remainder
    0.19
     contents
    0.19
     underside
    0.18
     workings
    0.17
    est
    0.17
     remnants
    0.16
    Activations Density 0.416%

    No Known Activations