© 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. 33095
    Prev
    Next
    INDEX
    Explanations

    immediately freed

    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
    Void
    -0.11
    ique
    -0.10
    026
    -0.10
    ocator
    -0.10
     Amen
    -0.10
    ridge
    -0.10
     dwind
    -0.09
    estroy
    -0.09
     brew
    -0.09
     inhabited
    -0.09
    POSITIVE LOGITS
     freed
    0.16
     immediately
    0.15
     freedom
    0.15
     freeing
    0.14
     Immediately
    0.14
     instantly
    0.14
     liberated
    0.13
     Freed
    0.13
     exposed
    0.13
     revealed
    0.12
    Activations Density 0.018%

    No Known Activations