© 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. 113817
    Prev
    Next
    INDEX
    Explanations

    Ijima

    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
     Cla
    -0.10
     cub
    -0.08
     revolution
    -0.08
     Cabr
    -0.07
    iner
    -0.07
    itre
    -0.07
     masc
    -0.07
     retrospective
    -0.07
    NF
    -0.06
     outsiders
    -0.06
    POSITIVE LOGITS
     nons
    0.12
     pepper
    0.11
     Pret
    0.10
     Companion
    0.10
    oha
    0.10
     moden
    0.10
     disg
    0.10
     unaffected
    0.10
    ophobic
    0.10
    orra
    0.10
    Activations Density 0.092%

    No Known Activations