© 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. 112871
    Prev
    Next
    INDEX
    Explanations

    finding locations or directions

    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
     readiness
    -0.10
    onent
    -0.10
    .force
    -0.10
    ê²°
    -0.09
    æĿŁ
    -0.09
    isti
    -0.09
    Force
    -0.09
     penetration
    -0.09
     Read
    -0.09
     internationally
    -0.09
    POSITIVE LOGITS
     locations
    0.27
     locating
    0.26
     locate
    0.26
     nearest
    0.23
     Locations
    0.22
     pointing
    0.22
     location
    0.22
     Locate
    0.22
     whereabouts
    0.21
     directions
    0.21
    Activations Density 0.339%

    No Known Activations