© 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. 115651
    Prev
    Next
    INDEX
    Explanations

    each

    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
    igham
    -0.09
     Yours
    -0.09
     Could
    -0.08
     MANY
    -0.08
     delegate
    -0.08
    inee
    -0.08
     Possibly
    -0.08
     equivalents
    -0.08
     Conte
    -0.08
    /renderer
    -0.07
    POSITIVE LOGITS
     each
    0.32
    Each
    0.30
     Each
    0.30
    each
    0.29
    æ¯ı
    0.23
     EACH
    0.22
    (each
    0.19
     кажд
    0.19
    _each
    0.18
     chaque
    0.18
    Activations Density 1.092%

    No Known Activations