© 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. 33688
    Prev
    Next
    INDEX
    Explanations

    living room, 36 km, furnished, motivated

    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
     segue
    -0.11
     shredd
    -0.11
    venture
    -0.11
     Stern
    -0.10
    shed
    -0.10
     Collider
    -0.10
     Abbott
    -0.10
     Shed
    -0.10
    voir
    -0.10
    uka
    -0.10
    POSITIVE LOGITS
    537
    0.09
     comb
    0.09
     services
    0.08
     autonomy
    0.08
     disabled
    0.08
     serv
    0.08
     service
    0.08
     coupling
    0.08
     Rooms
    0.08
     Serv
    0.08
    Activations Density 0.003%

    No Known Activations