© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5498
    Prev
    Next
    INDEX
    Explanations

    locations and descriptions

    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
    pz
    -0.12
    dre
    -0.12
    jem
    -0.11
     Kane
    -0.11
     Bair
    -0.11
    olg
    -0.11
     dash
    -0.10
    ONA
    -0.10
     Maver
    -0.10
    addon
    -0.10
    POSITIVE LOGITS
     tran
    0.10
     hydr
    0.09
    inge
    0.08
    rol
    0.08
     GD
    0.08
     shr
    0.08
    ear
    0.08
     Gin
    0.08
     Flores
    0.08
    angu
    0.07
    Activations Density 0.905%

    No Known Activations