© 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. 113142
    Prev
    Next
    INDEX
    Explanations

    understand and its implications

    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
     Bere
    -0.11
     exhaust
    -0.11
    Mapped
    -0.10
     Ful
    -0.10
    iesen
    -0.10
    onium
    -0.10
    onto
    -0.10
    astery
    -0.10
    DP
    -0.10
    port
    -0.10
    POSITIVE LOGITS
     perfectly
    0.16
     implicitly
    0.12
     completely
    0.10
    /ag
    0.09
     implicit
    0.08
     what
    0.08
    gan
    0.08
     words
    0.08
    mlin
    0.08
     vaguely
    0.08
    Activations Density 0.013%

    No Known Activations