© 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. 27474
    Prev
    Next
    INDEX
    Explanations

    eternal or perpetual states

    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
    oct
    -0.09
    ses
    -0.09
    otas
    -0.08
    tr
    -0.08
     Suff
    -0.08
    atore
    -0.07
    place
    -0.07
     ultimate
    -0.07
    acf
    -0.07
    onia
    -0.07
    POSITIVE LOGITS
    /rec
    0.14
    /internal
    0.14
     vigil
    0.13
    ibs
    0.12
    alling
    0.12
    quil
    0.11
    ising
    0.11
     damn
    0.11
     ago
    0.11
    /temp
    0.11
    Activations Density 0.038%

    No Known Activations