© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 4171
    Prev
    Next
    INDEX
    Explanations

    your neighbor

    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
    owell
    -0.10
    opher
    -0.09
    wers
    -0.09
    goo
    -0.09
     ident
    -0.08
    errick
    -0.08
     univers
    -0.08
    NESS
    -0.08
     myself
    -0.08
     goddess
    -0.08
    POSITIVE LOGITS
     your
    0.25
    your
    0.21
     YOUR
    0.19
    -your
    0.17
     neighbour
    0.17
     ваÑĪ
    0.17
     neighbor
    0.16
     THAT
    0.16
    Your
    0.15
     XYZ
    0.15
    Activations Density 0.272%

    No Known Activations