© 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. 7787
    Prev
    Next
    INDEX
    Explanations

    French or Spanish words or phrases

    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
    isme
    -0.11
    pth
    -0.11
    ات
    -0.11
     einz
    -0.10
    го
    -0.10
     erót
    -0.10
    ÑģÑĤÑĮ
    -0.10
    ÑĤÑĮ
    -0.10
    edic
    -0.10
    .Il
    -0.10
    POSITIVE LOGITS
     la
    0.12
    /of
    0.12
    inals
    0.08
     annum
    0.08
    rique
    0.08
     un
    0.08
     una
    0.08
     el
    0.07
    ificado
    0.07
    пиÑģание
    0.07
    Activations Density 0.146%

    No Known Activations