© 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. 91711
    Prev
    Next
    INDEX
    Explanations

    things are changing

    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
    ality
    -0.09
     Reco
    -0.08
    INA
    -0.08
     liá»ĩu
    -0.08
     Cornel
    -0.08
     Special
    -0.08
     Aurora
    -0.08
    yu
    -0.08
    abus
    -0.08
     cr
    -0.08
    POSITIVE LOGITS
     differently
    0.13
    /people
    0.12
    Things
    0.11
     escalate
    0.11
     arrang
    0.11
     Things
    0.10
    arra
    0.10
     deterior
    0.10
     ramp
    0.10
     escalating
    0.10
    Activations Density 0.049%

    No Known Activations