© 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. 25449
    Prev
    Next
    INDEX
    Explanations

    respecting value and integrity

    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
     smoothly
    -0.10
    uur
    -0.10
     satisfy
    -0.09
     Randolph
    -0.09
     safely
    -0.08
    rott
    -0.08
    _hor
    -0.08
    /legal
    -0.08
     convinc
    -0.08
    akk
    -0.08
    POSITIVE LOGITS
     dearly
    0.22
     greatly
    0.16
     immensely
    0.15
     valued
    0.15
     differently
    0.13
     enough
    0.13
     value
    0.13
     equally
    0.12
     cherish
    0.12
     integrity
    0.12
    Activations Density 0.058%

    No Known Activations