© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113120
    Prev
    Next
    INDEX
    Explanations

    age / enough to

    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
     sized
    -0.10
    sth
    -0.09
     overloaded
    -0.09
     Marl
    -0.09
     ready
    -0.08
     size
    -0.08
     continuation
    -0.08
     Musical
    -0.08
    alom
    -0.08
     surrogate
    -0.08
    POSITIVE LOGITS
     legally
    0.13
     remembers
    0.11
    jsc
    0.10
    remember
    0.10
    ought
    0.10
    xDE
    0.10
    okit
    0.10
     remember
    0.10
     married
    0.10
    _DS
    0.10
    Activations Density 0.003%

    No Known Activations