© 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. 91300
    Prev
    Next
    INDEX
    Explanations

    03 or Third

    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
     sixth
    -0.17
     fifth
    -0.17
     eighth
    -0.15
     fourth
    -0.14
     seventh
    -0.14
    Fourth
    -0.13
     Fifth
    -0.12
     Fourth
    -0.12
     ninth
    -0.12
     forth
    -0.11
    POSITIVE LOGITS
    3
    0.33
    ³
    0.28
     III
    0.27
    ï¼ĵ
    0.26
    ĥ
    0.25
     Third
    0.25
     third
    0.24
    03
    0.24
     THIRD
    0.24
     thirds
    0.23
    Activations Density 0.283%

    No Known Activations