© 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. 30758
    Prev
    Next
    INDEX
    Explanations

    free, full, good, batch, random

    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
    lessly
    -0.09
     indis
    -0.09
    kah
    -0.08
    ailable
    -0.08
     Yao
    -0.07
     Lad
    -0.07
    -wise
    -0.07
     Flames
    -0.07
    nh
    -0.07
     bumped
    -0.07
    POSITIVE LOGITS
    ern
    0.11
    —including
    0.11
    /at
    0.11
     feather
    0.10
    ilos
    0.10
    ano
    0.10
    047
    0.10
     noble
    0.10
    esti
    0.10
     affinity
    0.10
    Activations Density 0.324%

    No Known Activations