© 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. 116621
    Prev
    Next
    INDEX
    Explanations

    looking at a blank screen

    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
     observation
    -0.10
    peek
    -0.10
     Petr
    -0.09
     observ
    -0.09
     sal
    -0.09
     observers
    -0.09
    hey
    -0.09
     observational
    -0.09
     Observ
    -0.09
     Dro
    -0.09
    POSITIVE LOGITS
     blank
    0.16
     empty
    0.14
    blank
    0.11
     NOTHING
    0.11
     empt
    0.11
    ospace
    0.11
     screen
    0.11
    empty
    0.11
     screens
    0.11
     nothing
    0.11
    Activations Density 0.025%

    No Known Activations