© 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. 49671
    Prev
    Next
    INDEX
    Explanations

    code snippet delimiter

    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
    .ylabel
    -0.13
    ylabel
    -0.10
    mouseup
    -0.10
    _ylabel
    -0.10
     verbs
    -0.09
     throat
    -0.08
     screenHeight
    -0.08
    enheim
    -0.08
     trig
    -0.08
     UITableViewDelegate
    -0.08
    POSITIVE LOGITS
    xlabel
    0.12
    anko
    0.11
    .PostMapping
    0.11
    .RequestMapping
    0.11
    fw
    0.11
    _xlabel
    0.10
    .xlabel
    0.10
    _tabs
    0.10
     :↵↵↵↵
    0.10
    .JSONObject
    0.10
    Activations Density 1.323%

    No Known Activations