© 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. 31240
    Prev
    Next
    INDEX
    Explanations

    introducing lists or clauses

    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
    icode
    -0.08
    bab
    -0.08
    oad
    -0.08
    ERM
    -0.08
    YA
    -0.07
     lights
    -0.07
    LD
    -0.07
     metab
    -0.07
    etti
    -0.07
    dam
    -0.07
    POSITIVE LOGITS
     namely
    0.13
     viz
    0.11
    ephy
    0.10
     albeit
    0.10
    æļ
    0.10
    izon
    0.10
     intermediate
    0.10
    /original
    0.10
     sondern
    0.10
    gie
    0.10
    Activations Density 0.189%

    No Known Activations