© 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. 25943
    Prev
    Next
    INDEX
    Explanations

    available or occupied status

    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
     eliminated
    -0.09
     misplaced
    -0.09
     Irvine
    -0.09
    arya
    -0.09
     Becker
    -0.09
     blazing
    -0.09
     spl
    -0.09
    chor
    -0.09
    ofs
    -0.09
    oz
    -0.08
    POSITIVE LOGITS
     seats
    0.21
     spots
    0.17
     slots
    0.16
     Seats
    0.15
     rooms
    0.13
    /full
    0.13
     spaces
    0.13
     seat
    0.13
     space
    0.13
    slots
    0.13
    Activations Density 0.153%

    No Known Activations