© 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. 32581
    Prev
    Next
    INDEX
    Explanations

    de + number or nouns

    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
     de
    -0.10
    ache
    -0.08
     Tops
    -0.08
     vis
    -0.07
     pog
    -0.07
     Eck
    -0.07
     du
    -0.07
     Fen
    -0.07
     verbosity
    -0.07
     Chore
    -0.07
    POSITIVE LOGITS
     accord
    0.15
     afar
    0.14
     manera
    0.13
     haber
    0.13
    vido
    0.12
     côté
    0.11
     manner
    0.11
     manière
    0.11
     acuerdo
    0.11
     alta
    0.11
    Activations Density 0.072%

    No Known Activations