© 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. 113363
    Prev
    Next
    INDEX
    Explanations

    legal, ethical, or abstract concepts

    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
     sl
    -0.09
     sever
    -0.08
     meaning
    -0.08
     motive
    -0.08
    .ov
    -0.08
    aton
    -0.08
     spear
    -0.08
     Agu
    -0.07
     councils
    -0.07
     cob
    -0.07
    POSITIVE LOGITS
     etwa
    0.11
    ntag
    0.11
    sted
    0.11
    pio
    0.10
     saja
    0.10
    roach
    0.10
    iko
    0.10
    icum
    0.10
    prit
    0.10
     Abdel
    0.10
    Activations Density 0.307%

    No Known Activations