© 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. 49451
    Prev
    Next
    INDEX
    Explanations

    something to do

    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
    ì¶ľ
    -0.11
     Mesa
    -0.11
    /url
    -0.11
     deed
    -0.10
     deeds
    -0.10
     disgust
    -0.10
     balk
    -0.10
     craving
    -0.10
    Keith
    -0.10
    amer
    -0.09
    POSITIVE LOGITS
     dictate
    0.12
     freely
    0.11
    jian
    0.11
     sway
    0.10
    atron
    0.10
    icken
    0.09
    igo
    0.09
     lead
    0.08
    >čč↵
    0.08
     domination
    0.08
    Activations Density 0.038%

    No Known Activations