© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90103
    Prev
    Next
    INDEX
    Explanations

    rent and landlord

    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
     ign
    -0.09
    amba
    -0.08
    unt
    -0.08
     Tunis
    -0.08
     temper
    -0.08
    nia
    -0.08
    fleet
    -0.08
     Sweat
    -0.08
    ins
    -0.08
     Temper
    -0.07
    POSITIVE LOGITS
    payer
    0.11
    ertainment
    0.11
    ention
    0.10
    aal
    0.10
    hal
    0.10
    æĪ·
    0.10
    atura
    0.10
    ECH
    0.10
    apia
    0.10
     pij
    0.10
    Activations Density 0.012%

    No Known Activations