© 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. 31700
    Prev
    Next
    INDEX
    Explanations

    device, section, dreams, ground, book, statistics, neck, circuit, community

    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
     Katz
    -0.10
    aty
    -0.09
     multic
    -0.08
    chs
    -0.08
    yx
    -0.08
     ze
    -0.08
     Walk
    -0.08
     DW
    -0.08
     Abr
    -0.08
    Walk
    -0.07
    POSITIVE LOGITS
     who
    0.12
     fus
    0.12
     коÑĤоÑĢ
    0.12
    Fuse
    0.12
     whom
    0.11
    énom
    0.11
    known
    0.11
     called
    0.11
     that
    0.10
    ieten
    0.10
    Activations Density 0.689%

    No Known Activations