© 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. 116678
    Prev
    Next
    INDEX
    Explanations

    adjectives ending in -ed, -ed, -sized, -strong, -priced, -based, -winning

    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
    -going
    -0.12
     enough
    -0.12
    /we
    -0.12
    ingly
    -0.11
     nors
    -0.10
    -ish
    -0.10
    umu
    -0.10
    -legged
    -0.10
    -scale
    -0.10
     alot
    -0.09
    POSITIVE LOGITS
    /high
    0.10
    ,
    0.09
    urance
    0.08
    /-
    0.07
    "
    0.07
     (>
    0.07
     (<
    0.07
    /year
    0.07
    /version
    0.07
    Âł
    0.07
    Activations Density 0.614%

    No Known Activations