© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115393
    Prev
    Next
    INDEX
    Explanations

    cited case numbers and parentheticals

    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
     demean
    -0.08
     sage
    -0.07
    ARDS
    -0.07
     wise
    -0.07
     stray
    -0.07
     toolbar
    -0.07
     vile
    -0.07
    AGR
    -0.06
    InRange
    -0.06
     surplus
    -0.06
    POSITIVE LOGITS
     strang
    0.11
    rray
    0.10
    /values
    0.10
     Kap
    0.10
     Cald
    0.10
    stery
    0.10
    CAP
    0.09
     cen
    0.09
     bored
    0.09
     rig
    0.09
    Activations Density 0.558%

    No Known Activations