© 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. 5992
    Prev
    Next
    INDEX
    Explanations

    fall and falling

    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
     Essen
    -0.11
    asso
    -0.11
    villa
    -0.11
    nde
    -0.11
    iger
    -0.10
    evin
    -0.10
     fingerprint
    -0.10
    dna
    -0.10
    ellig
    -0.10
    ès
    -0.10
    POSITIVE LOGITS
     onto
    0.19
     asleep
    0.15
    onto
    0.14
     schwer
    0.14
     prey
    0.14
    trap
    0.13
     trap
    0.13
     fall
    0.12
     traps
    0.12
     grace
    0.12
    Activations Density 0.235%

    No Known Activations