© 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. 18149
    Prev
    Next
    INDEX
    Explanations

    leaving or exiting

    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
    immers
    -0.13
     Replay
    -0.11
     Bien
    -0.10
    esan
    -0.10
     Rescue
    -0.10
    NG
    -0.10
     Jak
    -0.10
     Hacker
    -0.10
     Attached
    -0.10
     jak
    -0.10
    POSITIVE LOGITS
     altogether
    0.13
     entirely
    0.10
     leaving
    0.10
     leave
    0.09
     door
    0.09
    adder
    0.09
     undecided
    0.08
    sta
    0.08
     exit
    0.08
     via
    0.08
    Activations Density 0.023%

    No Known Activations