© 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. 25966
    Prev
    Next
    INDEX
    Explanations

    possessive followed by noun describing characteristic

    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
     personal
    -0.13
     personally
    -0.12
     voice
    -0.12
     movements
    -0.11
     senses
    -0.11
     Bernstein
    -0.10
     testimony
    -0.10
    personal
    -0.10
    amina
    -0.10
     authored
    -0.10
    POSITIVE LOGITS
     founder
    0.17
     mascot
    0.15
     founders
    0.14
     flagship
    0.14
     motto
    0.14
     logo
    0.12
     raison
    0.12
     slogan
    0.12
     lineup
    0.11
     offerings
    0.11
    Activations Density 0.532%

    No Known Activations