© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 87921
    Prev
    Next
    INDEX
    Explanations

    laxness, freedom, and tolerance

    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
     unavoid
    -0.12
     obligatory
    -0.12
     painstaking
    -0.11
     compulsory
    -0.10
     jer
    -0.10
     compuls
    -0.10
    Unavailable
    -0.10
    emet
    -0.09
     unavoidable
    -0.09
    opo
    -0.09
    POSITIVE LOGITS
     relaxed
    0.28
     lax
    0.26
     laisse
    0.25
     loosen
    0.24
     attitude
    0.24
     freedom
    0.22
     freely
    0.21
     tolerant
    0.21
     relax
    0.21
     relaxing
    0.20
    Activations Density 0.381%

    No Known Activations