© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 91897
    Prev
    Next
    INDEX
    Explanations

    suppose

    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
     aforementioned
    -0.09
     Alexand
    -0.08
    ellido
    -0.08
    ‘s
    -0.08
     Advertisement
    -0.08
     However
    -0.07
    errs
    -0.07
    CAP
    -0.07
     youre
    -0.07
     Geoffrey
    -0.07
    POSITIVE LOGITS
     awe
    0.11
    Å¡
    0.11
     Sac
    0.10
    ids
    0.10
     vic
    0.10
     aff
    0.10
     Cron
    0.10
    OME
    0.09
     gentleman
    0.09
     sac
    0.09
    Activations Density 0.028%

    No Known Activations