© 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. 5973
    Prev
    Next
    INDEX
    Explanations

    log in/on

    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
     Rec
    -0.11
     Kont
    -0.11
    asts
    -0.10
    iez
    -0.10
     lined
    -0.10
     recip
    -0.10
     lining
    -0.10
     Vac
    -0.10
    ened
    -0.09
     threaded
    -0.09
    POSITIVE LOGITS
     onto
    0.17
     into
    0.14
    /logout
    0.11
     Ont
    0.10
     off
    0.09
    [source
    0.09
    -off
    0.09
    efe
    0.09
    onto
    0.09
    /log
    0.09
    Activations Density 0.007%

    No Known Activations