© 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. 6835
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
     —↵↵
    -0.12
     obr
    -0.11
     exped
    -0.09
    ucci
    -0.09
     «
    -0.09
     Intern
    -0.09
     sliding
    -0.08
     moto
    -0.08
    Intern
    -0.08
    ãĢĮ
    -0.08
    POSITIVE LOGITS
    verter
    0.09
     Dise
    0.09
     Mans
    0.09
     Sellers
    0.09
     compat
    0.09
     STYLE
    0.08
    ENAME
    0.08
    DataStream
    0.08
     destined
    0.08
    ierce
    0.08
    Activations Density 0.001%

    No Known Activations