© 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. 30824
    Prev
    Next
    INDEX
    Explanations

    MF16, FC Group, faan Ali

    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
     fond
    -0.11
    frame
    -0.11
     fucking
    -0.11
    file
    -0.11
    fur
    -0.11
    frequency
    -0.10
    flow
    -0.10
     fortified
    -0.10
    ÑĦоÑĢм
    -0.10
     frequ
    -0.10
    POSITIVE LOGITS
    entimes
    0.16
    ication
    0.16
    uentes
    0.16
    actory
    0.14
    usion
    0.14
    teenth
    0.13
    ancybox
    0.13
    alcon
    0.13
    initely
    0.12
    icient
    0.12
    Activations Density 1.763%

    No Known Activations