© 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. 14875
    Prev
    Next
    INDEX
    Explanations

    freeing/relief/liberation

    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
     Wall
    -0.09
    stub
    -0.09
    iche
    -0.09
    achu
    -0.09
     Maz
    -0.09
    Witness
    -0.09
     Kal
    -0.09
    ali
    -0.09
     Stark
    -0.09
    allest
    -0.09
    POSITIVE LOGITS
     freeing
    0.54
     frees
    0.47
     freed
    0.41
     relie
    0.36
     relieve
    0.34
     Freed
    0.33
     relieved
    0.29
     relief
    0.25
     liber
    0.25
     allev
    0.25
    Activations Density 0.354%

    No Known Activations