© 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. 115706
    Prev
    Next
    INDEX
    Explanations

    Lou names

    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
    enha
    -0.10
     Wish
    -0.08
    mars
    -0.08
     Hoy
    -0.08
     tempor
    -0.08
    -medium
    -0.08
     Uns
    -0.08
     mult
    -0.08
    weis
    -0.08
    busters
    -0.07
    POSITIVE LOGITS
    isa
    0.16
     lou
    0.14
    loud
    0.13
    Lou
    0.13
    ie
    0.12
     louder
    0.12
    cks
    0.12
    idor
    0.12
    ise
    0.11
     loud
    0.11
    Activations Density 0.009%

    No Known Activations