© 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. 50502
    Prev
    Next
    INDEX
    Explanations

    aspects of life

    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
     Hein
    -0.09
     mirror
    -0.08
     Fla
    -0.08
     tail
    -0.08
     ado
    -0.08
     assort
    -0.08
     lav
    -0.08
    /mod
    -0.07
    ~-
    -0.07
     lev
    -0.07
    POSITIVE LOGITS
     existence
    0.21
     organs
    0.16
     fibers
    0.15
     cells
    0.15
     body
    0.15
     pores
    0.15
     fiber
    0.14
    existence
    0.14
    /body
    0.13
     entirety
    0.13
    Activations Density 0.022%

    No Known Activations