© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46298
    Prev
    Next
    INDEX
    Explanations

    cam naming convention

    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
     offs
    -0.13
     Sampler
    -0.11
     caul
    -0.10
    iÃŁ
    -0.10
    chs
    -0.10
    lamp
    -0.10
    kah
    -0.10
     cane
    -0.10
    lap
    -0.10
    ushima
    -0.10
    POSITIVE LOGITS
    eras
    0.13
    -equipped
    0.13
     footage
    0.12
    ming
    0.12
    shaft
    0.12
    -enabled
    0.12
    ouflage
    0.11
    /web
    0.10
    bers
    0.10
    /audio
    0.10
    Activations Density 0.029%

    No Known Activations