© 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. 91470
    Prev
    Next
    INDEX
    Explanations

    per unit or rate

    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
    emark
    -0.13
     Malcolm
    -0.10
     Annual
    -0.10
     SY
    -0.10
    aal
    -0.10
    adas
    -0.10
    ë¶Ħ
    -0.10
    /mark
    -0.10
    ipa
    -0.10
    HY
    -0.09
    POSITIVE LOGITS
     per
    0.56
    _per
    0.29
    per
    0.27
     Per
    0.24
    -per
    0.23
     PER
    0.21
    .per
    0.20
    (per
    0.20
    Per
    0.19
    _PER
    0.18
    Activations Density 0.414%

    No Known Activations