© 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. 29445
    Prev
    Next
    INDEX
    Explanations

    rest, rest/, rest-api, rest-kit, restic

    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
    ity
    -0.10
    ALLY
    -0.09
     Apt
    -0.08
    ibble
    -0.08
     rang
    -0.08
    ìĦ
    -0.08
    CADE
    -0.08
    esson
    -0.08
    cl
    -0.08
    erate
    -0.08
    POSITIVE LOGITS
    orative
    0.28
    aurants
    0.20
    ful
    0.20
     assured
    0.20
    orer
    0.19
    RICT
    0.18
    atement
    0.17
    repo
    0.16
    _framework
    0.15
    ocking
    0.15
    Activations Density 0.077%

    No Known Activations