© 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. 49555
    Prev
    Next
    INDEX
    Explanations

    indoors or 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
     roadside
    -0.12
    Parking
    -0.12
    eken
    -0.12
     parking
    -0.12
     emb
    -0.11
     Parking
    -0.10
     faint
    -0.10
     parach
    -0.10
     playa
    -0.10
     ascending
    -0.10
    POSITIVE LOGITS
     home
    0.22
     indoors
    0.19
     domestic
    0.17
    home
    0.16
     indoor
    0.16
     house
    0.15
    /home
    0.14
     domest
    0.14
     domestically
    0.14
    _home
    0.14
    Activations Density 0.069%

    No Known Activations