© 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. 47540
    Prev
    Next
    INDEX
    Explanations

    door words

    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
     bum
    -0.14
     bö
    -0.12
    ãģĽ
    -0.11
     goede
    -0.11
     è¾ĵ
    -0.11
     chan
    -0.11
     Tomas
    -0.11
     komt
    -0.11
     scav
    -0.11
     Evangel
    -0.10
    POSITIVE LOGITS
     door
    0.11
    door
    0.11
     Door
    0.10
    eer
    0.09
     doors
    0.09
    oor
    0.09
    _door
    0.08
    oon
    0.08
     wo
    0.08
     Coast
    0.08
    Activations Density 0.001%

    No Known Activations