© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 8109
    Prev
    Next
    INDEX
    Explanations

    criminal use, singles, solve, elections

    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
    Negative Logits
    T
    -0.19
    R
    -0.19
    E
    -0.18
    C
    -0.18
    ERSHEY
    -0.18
    P
    -0.17
    S
    -0.17
    L
    -0.15
    D
    -0.15
    M
    -0.15
    POSITIVE LOGITS
    etheless
    0.16
    tlement
    0.13
    aug
    0.13
    IA
    0.13
    dea
    0.13
    .E
    0.13
    IO
    0.12
    INS
    0.12
    .A
    0.12
    auf
    0.12
    Activations Density 0.938%

    No Known Activations