© 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. 112455
    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
    .boolean
    -0.09
    ibold
    -0.09
     inhal
    -0.09
     inh
    -0.09
    002
    -0.09
    nos
    -0.09
     remotely
    -0.09
    éĢģ
    -0.08
     cond
    -0.08
    remote
    -0.08
    POSITIVE LOGITS
     outside
    0.15
     exit
    0.14
     away
    0.13
     Outside
    0.12
     exiting
    0.12
     Exiting
    0.11
     exited
    0.11
     out
    0.11
     Exit
    0.11
    outside
    0.11
    Activations Density 0.095%

    No Known Activations