© 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. 7338
    Prev
    Next
    INDEX
    Explanations

    has been shown to

    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
     Lal
    -0.10
    echa
    -0.10
    ache
    -0.09
    LOT
    -0.09
    idar
    -0.09
     Hass
    -0.08
    rez
    -0.08
    365
    -0.08
    eon
    -0.08
    idl
    -0.08
    POSITIVE LOGITS
     repeatedly
    0.25
     consistently
    0.17
     elsewhere
    0.16
     proven
    0.13
     conclus
    0.13
     shown
    0.13
     show
    0.12
     repet
    0.11
     experiment
    0.11
    shown
    0.11
    Activations Density 0.455%

    No Known Activations