© 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. 5171
    Prev
    Next
    INDEX
    Explanations

    Luoyang Bridge, Liuyang, Liushan, Zhangbu, Fuzhengzengxiao, Leshan, aorta, Wuhan–Yichang

    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
     committed
    -0.10
     âĢŀ
    -0.10
     âĢº
    -0.10
    ĥĿ
    -0.09
    trade
    -0.09
     Phon
    -0.09
    enty
    -0.09
     soap
    -0.09
     dem
    -0.09
     Erot
    -0.09
    POSITIVE LOGITS
    umen
    0.12
     è¾ĵ
    0.11
    angling
    0.10
     cong
    0.10
    ang
    0.10
     sect
    0.09
    amen
    0.09
     proport
    0.09
     congr
    0.09
    MLS
    0.09
    Activations Density 0.038%

    No Known Activations