© 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. 47239
    Prev
    Next
    INDEX
    Explanations

    positioning and location analysis

    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
     flakes
    -0.11
     Notices
    -0.11
    Scalars
    -0.11
     kle
    -0.10
     Kits
    -0.10
     mascara
    -0.10
     sharpen
    -0.10
     razor
    -0.10
     notices
    -0.10
     Membership
    -0.10
    POSITIVE LOGITS
     positions
    0.19
     positional
    0.19
     Positions
    0.18
    Positions
    0.18
     biome
    0.17
    positions
    0.16
     geometry
    0.15
     positioning
    0.15
     geomet
    0.15
     ergonomic
    0.15
    Activations Density 0.254%

    No Known Activations