© 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. 112746
    Prev
    Next
    INDEX
    Explanations

    carefully chosen, sterilized, observation

    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
     immedi
    -0.13
     gladly
    -0.12
    kie
    -0.11
     relentlessly
    -0.10
     sooner
    -0.10
     willingly
    -0.10
     shorten
    -0.10
     freely
    -0.10
    asse
    -0.10
     unlucky
    -0.09
    POSITIVE LOGITS
     lest
    0.25
     carefully
    0.22
     careful
    0.18
     avoiding
    0.18
     avoid
    0.18
     delicate
    0.18
     avoided
    0.17
    lest
    0.17
    avoid
    0.17
     avoids
    0.16
    Activations Density 0.049%

    No Known Activations