© 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. 90768
    Prev
    Next
    INDEX
    Explanations

    adjectives describing 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
    /Dk
    -0.17
    ï¼Īç¬ij
    -0.14
    (and
    -0.14
    /=
    -0.14
    /MPL
    -0.14
     bzw
    -0.13
    ï¼ı
    -0.13
    aket
    -0.13
    +B
    -0.13
    /***/
    -0.13
    POSITIVE LOGITS
     yet
    0.14
    kes
    0.07
     but
    0.06
     maks
    0.06
     yes
    0.06
    ikes
    0.06
     foremost
    0.06
    yet
    0.06
    ,t
    0.06
     Yet
    0.06
    Activations Density 0.112%

    No Known Activations