© 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. 117036
    Prev
    Next
    INDEX
    Explanations

    which phrases

    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
     skew
    -0.06
     clutter
    -0.06
    ÛĮر
    -0.06
     foremost
    -0.06
    irit
    -0.06
    Ĭ¶
    -0.06
    itial
    -0.06
    nl
    -0.06
     vanilla
    -0.06
    abouts
    -0.05
    POSITIVE LOGITS
     begs
    0.17
     reminds
    0.16
     means
    0.16
     explains
    0.15
     brings
    0.15
     Means
    0.14
     basically
    0.14
     begged
    0.13
     Wich
    0.13
    means
    0.13
    Activations Density 0.011%

    No Known Activations