© 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. 92258
    Prev
    Next
    INDEX
    Explanations

    names and software starting with N, Ng, or Nigg

    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
    /ex
    -0.11
     quar
    -0.11
    ical
    -0.10
     Cecil
    -0.10
    peg
    -0.10
     Quar
    -0.09
    ived
    -0.09
     pity
    -0.09
     minded
    -0.09
    æĶ¿
    -0.09
    POSITIVE LOGITS
    eli
    0.11
     neglected
    0.11
    uyen
    0.11
    appa
    0.08
     Volk
    0.08
     Trit
    0.08
    vod
    0.08
    Kelly
    0.08
     whit
    0.08
    entropy
    0.08
    Activations Density 0.034%

    No Known Activations