© 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. 25393
    Prev
    Next
    INDEX
    Explanations

    what is happening

    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
    AGE
    -0.13
    StateException
    -0.12
    olina
    -0.12
    \$
    -0.12
    nik
    -0.12
     even
    -0.12
    mono
    -0.12
    éra
    -0.11
    argar
    -0.11
    /js
    -0.11
    POSITIVE LOGITS
     happening
    0.07
     further
    0.07
     apt
    0.07
     happen
    0.07
     scop
    0.06
     aims
    0.06
     Yoshi
    0.06
     eventual
    0.06
     unre
    0.06
     Troy
    0.06
    Activations Density 0.084%

    No Known Activations