© 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. 116818
    Prev
    Next
    INDEX
    Explanations

    Submitted by admin

    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
    toa
    -0.12
    MLS
    -0.10
    outu
    -0.10
    ValuePair
    -0.09
     rue
    -0.09
     Carp
    -0.09
    .ml
    -0.09
     absl
    -0.09
    CLU
    -0.09
     CPF
    -0.09
    POSITIVE LOGITS
    admin
    0.22
     Admin
    0.21
    _admin
    0.19
     admin
    0.19
    Admin
    0.19
    -admin
    0.18
    _Admin
    0.18
     administrator
    0.15
     Team
    0.15
     Administrator
    0.15
    Activations Density 0.199%

    No Known Activations