© 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. 6423
    Prev
    Next
    INDEX
    Explanations

    stillness and being static

    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
     continually
    -0.12
     continuously
    -0.11
    /message
    -0.10
    ahir
    -0.10
    -minus
    -0.10
     STILL
    -0.10
    esson
    -0.10
     glory
    -0.10
     openly
    -0.10
    rij
    -0.10
    POSITIVE LOGITS
    ness
    0.16
    er
    0.10
    NESS
    0.09
    (er
    0.09
    zin
    0.08
    lest
    0.08
     McK
    0.08
    iard
    0.08
    idas
    0.08
    ouro
    0.08
    Activations Density 0.022%

    No Known Activations