© 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. 47387
    Prev
    Next
    INDEX
    Explanations

    off to

    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
    emma
    -0.12
    ittal
    -0.11
    ãģĪ
    -0.11
    /block
    -0.10
    Hits
    -0.10
     wann
    -0.10
    dio
    -0.10
     Blow
    -0.10
    Fuse
    -0.10
     kino
    -0.10
    POSITIVE LOGITS
     toward
    0.11
     to
    0.11
     towards
    0.11
     into
    0.10
    Towards
    0.10
     Towards
    0.10
     punct
    0.10
     downhill
    0.10
     Tow
    0.09
    -o
    0.09
    Activations Density 0.020%

    No Known Activations