© 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. 88055
    Prev
    Next
    INDEX
    Explanations

    nature

    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
    Sizer
    -0.10
     Fr
    -0.09
    anos
    -0.09
    loi
    -0.09
    )+(
    -0.09
    ulis
    -0.09
     Cel
    -0.09
     Wich
    -0.08
    iec
    -0.08
    _hint
    -0.08
    POSITIVE LOGITS
     nature
    0.52
     aspect
    0.47
    nature
    0.39
     aspects
    0.38
    aspect
    0.34
     Nature
    0.31
    Nature
    0.31
     Aspect
    0.31
    Aspect
    0.25
    ness
    0.21
    Activations Density 0.242%

    No Known Activations