© 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. 25699
    Prev
    Next
    INDEX
    Explanations

    searching and locating physically

    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
     observation
    -0.10
     ogl
    -0.09
    derived
    -0.09
     Extraction
    -0.09
     spit
    -0.09
     viewing
    -0.09
    observation
    -0.09
     watching
    -0.09
     gaz
    -0.08
    resh
    -0.08
    POSITIVE LOGITS
     blindly
    0.25
     grop
    0.22
     searching
    0.19
     search
    0.19
     locate
    0.17
     locating
    0.17
     tactile
    0.16
     searches
    0.16
     blind
    0.16
    search
    0.16
    Activations Density 0.026%

    No Known Activations