© 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. 46577
    Prev
    Next
    INDEX
    Explanations

    `ation` following device and system types

    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
     inert
    -0.11
     Lent
    -0.10
    inge
    -0.10
     Carp
    -0.10
     Struct
    -0.10
    azzo
    -0.10
    drv
    -0.10
    cff
    -0.10
    olg
    -0.10
     Bernstein
    -0.10
    POSITIVE LOGITS
     cres
    0.09
     POV
    0.08
     Laurent
    0.08
     van
    0.08
     Dios
    0.07
    olina
    0.07
    337
    0.07
    ee
    0.07
    anya
    0.07
    van
    0.07
    Activations Density 0.080%

    No Known Activations