© 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. 6597
    Prev
    Next
    INDEX
    Explanations

    features and technologies

    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
    ãģĿãģĹãģ¦
    -0.17
    ãģĵãĤĵ
    -0.15
    ãģĹãģĭ
    -0.14
    ãģĹãģĭãģĹ
    -0.12
     mirrored
    -0.12
    ãģ¾ãģŁ
    -0.11
    ãģ¡ãģ¯
    -0.11
    urma
    -0.11
     emailed
    -0.11
    ãģŁãģł
    -0.11
    POSITIVE LOGITS
    ãĥ»ãĥ»ãĥ»↵↵
    0.22
    ･･
    0.22
    âĻª↵↵
    0.20
    ãĢĢ
    0.20
     ãĥ»
    0.20
    âĢ»
    0.19
     âĢ»
    0.19
    ãĥ»
    0.18
    ãĥ»ãĥ»
    0.16
    ãģĤãĤĬãģĮ
    0.15
    Activations Density 3.966%

    No Known Activations