© 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. 90633
    Prev
    Next
    INDEX
    Explanations

    X- prefix generator

    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
     peg
    -0.12
    outh
    -0.11
    _epi
    -0.11
    herit
    -0.10
     GW
    -0.10
    edian
    -0.10
    leep
    -0.10
     neigh
    -0.10
    ken
    -0.10
     virtually
    -0.10
    POSITIVE LOGITS
    appa
    0.09
    boa
    0.08
     Gra
    0.08
    rays
    0.08
     chromosome
    0.07
    MH
    0.07
    erne
    0.07
    pulse
    0.07
    -Men
    0.07
    .tx
    0.07
    Activations Density 0.043%

    No Known Activations