© 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. 90933
    Prev
    Next
    INDEX
    Explanations

    achieved, maintained, protected, provided

    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
    ENN
    -0.10
     escal
    -0.09
     esc
    -0.09
     Mood
    -0.08
    ноп
    -0.08
    á»ijng
    -0.08
     Unauthorized
    -0.08
    лав
    -0.08
     ineligible
    -0.08
     ticking
    -0.08
    POSITIVE LOGITS
     achieved
    0.22
     achievable
    0.18
     Achie
    0.18
     maintained
    0.17
     restored
    0.17
     attained
    0.17
     afforded
    0.16
     preserved
    0.15
     enforced
    0.15
     achieve
    0.15
    Activations Density 0.394%

    No Known Activations