© 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. 88794
    Prev
    Next
    INDEX
    Explanations

    's Health

    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
     Hanson
    -0.09
     trem
    -0.08
     overhead
    -0.07
     Palmer
    -0.07
     pay
    -0.07
    amon
    -0.07
     Trem
    -0.07
    bak
    -0.07
     GI
    -0.07
    ToF
    -0.06
    POSITIVE LOGITS
    edd
    0.12
     Dove
    0.12
     Streets
    0.12
     Msg
    0.10
    ptions
    0.10
     streets
    0.10
    issen
    0.10
     ë²Ħ
    0.10
     PIC
    0.10
     Tun
    0.10
    Activations Density 0.001%

    No Known Activations