© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114942
    Prev
    Next
    INDEX
    Explanations

    barrier impairment

    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
    ajs
    -0.08
    erring
    -0.08
    oop
    -0.08
    929
    -0.07
     Commonwealth
    -0.07
     parti
    -0.07
     Sloan
    -0.07
    erin
    -0.07
     runner
    -0.07
    erp
    -0.07
    POSITIVE LOGITS
     badly
    0.11
     cont
    0.11
     McCarthy
    0.10
     menor
    0.10
    isa
    0.10
     upwards
    0.10
     lenght
    0.10
    éķ¿åº¦
    0.10
     Barker
    0.10
    wand
    0.10
    Activations Density 0.002%

    No Known Activations