© 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. 116644
    Prev
    Next
    INDEX
    Explanations

    programming help requests

    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
    s
    -0.27
    sheets
    -0.12
    sar
    -0.11
    sav
    -0.11
    sburg
    -0.11
    oria
    -0.10
    sip
    -0.10
    sst
    -0.10
    entic
    -0.09
    Ñĭ
    -0.09
    POSITIVE LOGITS
    ÑĤе
    0.17
    ÑģÑĤв
    0.13
    ÑĤи
    0.11
    Ñı
    0.10
    ÑģÑı
    0.10
    Ñıд
    0.10
     Dalton
    0.10
    ков
    0.10
    rica
    0.09
    antro
    0.09
    Activations Density 0.044%

    No Known Activations