© 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. 16636
    Prev
    Next
    INDEX
    Explanations

    down or search

    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
    ::*
    -0.10
    Paren
    -0.10
    _plan
    -0.09
    ihan
    -0.09
     Fest
    -0.09
     horizon
    -0.09
     choked
    -0.09
    ::__
    -0.09
    .Level
    -0.09
    ropolis
    -0.09
    POSITIVE LOGITS
     spine
    0.12
     torso
    0.12
    /back
    0.11
     back
    0.11
    /ac
    0.11
     Backbone
    0.10
     drop
    0.10
     downwards
    0.09
    ãģ¾
    0.09
     towards
    0.09
    Activations Density 0.006%

    No Known Activations