© 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. 6691
    Prev
    Next
    INDEX
    Explanations

    action outcome or consequence

    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
     exists
    -0.09
    exists
    -0.09
     kindly
    -0.09
     Mig
    -0.09
    ARA
    -0.09
     sworn
    -0.08
    otor
    -0.08
    HELL
    -0.08
     exist
    -0.08
    ewan
    -0.08
    POSITIVE LOGITS
     causes
    0.16
     causing
    0.14
     cause
    0.14
     ceased
    0.14
    cause
    0.14
     slowed
    0.13
     Causes
    0.13
     Cause
    0.13
     disrupted
    0.12
     became
    0.12
    Activations Density 0.036%

    No Known Activations