© 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. 114403
    Prev
    Next
    INDEX
    Explanations

    to log, to namespace, to 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
    ower
    -0.08
    dong
    -0.08
     grief
    -0.08
     replicas
    -0.08
    ovi
    -0.08
    ibo
    -0.08
    awe
    -0.07
     Dort
    -0.07
    backs
    -0.07
     happiness
    -0.07
    POSITIVE LOGITS
     herself
    0.14
     himself
    0.12
     yourself
    0.12
     themselves
    0.12
     indicates
    0.11
     indicate
    0.11
     oneself
    0.11
     indicating
    0.11
     itself
    0.10
     invisible
    0.10
    Activations Density 0.005%

    No Known Activations