© 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. 25825
    Prev
    Next
    INDEX
    Explanations

    names ending in -ags or -ages

    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
    rlen
    -0.12
    ural
    -0.12
     Pru
    -0.11
     prevailing
    -0.10
    rary
    -0.10
     stabil
    -0.10
     Vog
    -0.10
    indo
    -0.10
     Hamp
    -0.10
    uate
    -0.10
    POSITIVE LOGITS
    anke
    0.10
    heimer
    0.09
    Tot
    0.08
     Quar
    0.08
     veteran
    0.08
     quar
    0.08
     discharge
    0.07
    Drag
    0.07
     amateur
    0.07
     hanging
    0.07
    Activations Density 0.013%

    No Known Activations