© 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. 6110
    Prev
    Next
    INDEX
    Explanations

    file or article are

    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
     Bout
    -0.12
     classic
    -0.11
     Buen
    -0.10
    OLE
    -0.09
    shr
    -0.09
     Rede
    -0.09
    imon
    -0.09
    NIL
    -0.09
     Shack
    -0.09
    zl
    -0.08
    POSITIVE LOGITS
     lashes
    0.12
    aska
    0.10
    (s
    0.10
    ISTER
    0.10
    atis
    0.10
    entifier
    0.10
    (es
    0.10
     Jas
    0.10
    æ¹
    0.09
     scrambled
    0.09
    Activations Density 0.434%

    No Known Activations