© 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. 91970
    Prev
    Next
    INDEX
    Explanations

    gate, door, opening, closing, switch

    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
    sek
    -0.11
     Estr
    -0.09
     estr
    -0.09
    endon
    -0.08
    DCF
    -0.08
    fad
    -0.08
    iros
    -0.08
    feld
    -0.08
     Freak
    -0.08
     fread
    -0.08
    POSITIVE LOGITS
     open
    0.17
    -open
    0.13
     OPEN
    0.12
    open
    0.12
    .open
    0.11
    _open
    0.11
     closed
    0.10
    å¼
    0.10
     Lindsey
    0.10
    /open
    0.10
    Activations Density 0.002%

    No Known Activations