© 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. 90550
    Prev
    Next
    INDEX
    Explanations

    man is like a prisoner

    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
    566
    -0.10
     authorize
    -0.07
    082
    -0.07
    wel
    -0.07
    omen
    -0.07
     childish
    -0.07
     sober
    -0.07
     saying
    -0.07
    ocker
    -0.06
    ssi
    -0.06
    POSITIVE LOGITS
     gotta
    0.13
     Frontier
    0.13
     Embedded
    0.12
     embedded
    0.12
     Anth
    0.11
    resp
    0.11
     Sharma
    0.11
     mixes
    0.11
     Vid
    0.11
     lik
    0.11
    Activations Density 0.005%

    No Known Activations