© 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. 32350
    Prev
    Next
    INDEX
    Explanations

    time stamp

    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
     sounding
    -0.12
     visibility
    -0.09
     invis
    -0.09
    ipl
    -0.09
     wl
    -0.09
     soundtrack
    -0.08
    mars
    -0.08
     sounds
    -0.08
    lav
    -0.08
     observable
    -0.08
    POSITIVE LOGITS
     squarely
    0.16
     sideways
    0.16
     closely
    0.16
     towards
    0.15
     toward
    0.15
    çľ
    0.14
     attent
    0.14
     naar
    0.13
     fond
    0.12
     horizon
    0.12
    Activations Density 0.348%

    No Known Activations