© 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. 27618
    Prev
    Next
    INDEX
    Explanations

    at home

    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
     Sto
    -0.12
     balanced
    -0.11
     pockets
    -0.10
     hum
    -0.10
     brought
    -0.09
     attachments
    -0.09
     Lav
    -0.09
     Bowl
    -0.09
     Station
    -0.09
    rides
    -0.09
    POSITIVE LOGITS
     home
    0.21
     alone
    0.19
     Alone
    0.19
    -alone
    0.19
    alone
    0.17
    (home
    0.16
     daytime
    0.15
    home
    0.14
     HOME
    0.14
     homeowners
    0.14
    Activations Density 0.108%

    No Known Activations