© 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. 47468
    Prev
    Next
    INDEX
    Explanations

    FLAC, F, HF, PF

    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
     Malk
    -0.12
     TMP
    -0.11
    .newBuilder
    -0.10
     Tob
    -0.10
     Kemp
    -0.10
     CPI
    -0.10
    nos
    -0.10
     bail
    -0.10
     pard
    -0.10
     wor
    -0.10
    POSITIVE LOGITS
     HF
    0.23
     PF
    0.22
    MF
    0.21
     MF
    0.21
     F
    0.21
    HF
    0.21
    NF
    0.21
    PF
    0.20
    xF
    0.20
     SF
    0.20
    Activations Density 0.466%

    No Known Activations