© 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. 4810
    Prev
    Next
    INDEX
    Explanations

    external or outside

    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
     upfront
    -0.11
     undercover
    -0.11
     backstage
    -0.10
     oro
    -0.10
    ween
    -0.10
     overseas
    -0.09
     Klaus
    -0.09
     offshore
    -0.09
    gere
    -0.09
    gone
    -0.09
    POSITIVE LOGITS
    Outside
    0.17
     Outside
    0.17
     External
    0.16
     external
    0.16
     outside
    0.16
    /Internal
    0.14
     exterior
    0.14
    å¤ĸ
    0.14
    outside
    0.13
    External
    0.13
    Activations Density 0.277%

    No Known Activations