© 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. 112083
    Prev
    Next
    INDEX
    Explanations

    found themselves in a state

    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
    atis
    -0.11
    evin
    -0.11
     davon
    -0.10
    -0.10
     Lu
    -0.09
     fleece
    -0.09
    ambre
    -0.09
     toll
    -0.09
     lur
    -0.09
     Tol
    -0.09
    POSITIVE LOGITS
     unable
    0.17
     needing
    0.17
     facing
    0.15
     surrounded
    0.13
     faced
    0.13
     confronted
    0.12
     amidst
    0.11
     Unable
    0.11
     immersed
    0.11
     alone
    0.11
    Activations Density 0.022%

    No Known Activations