© 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. 4138
    Prev
    Next
    INDEX
    Explanations

    location or position finding

    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
     Severity
    -0.11
    /print
    -0.09
     previews
    -0.09
     appraisal
    -0.09
     Transfer
    -0.09
     grad
    -0.09
    legacy
    -0.09
    tape
    -0.09
    fan
    -0.08
     tast
    -0.08
    POSITIVE LOGITS
     whereabouts
    0.48
     location
    0.35
     locations
    0.31
     Location
    0.30
    Location
    0.27
    -location
    0.27
    location
    0.26
     LOCATION
    0.26
     Locations
    0.25
    Locations
    0.24
    Activations Density 0.354%

    No Known Activations