© 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. 112328
    Prev
    Next
    INDEX
    Explanations

    ãģĤãĤĬãģĪãģĮ orãģĤãĤĬãģĮ language-specific characters

    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
    ãģĹãģĭ
    -0.17
    ï¼ķ
    -0.16
    ãģĵãĤĵ
    -0.16
    ãģŁãģł
    -0.15
    ï¼Ĵï¼IJ
    -0.15
    ç»
    -0.15
    ãĢģ↵↵
    -0.14
    ...↵↵↵↵
    -0.14
    åıij
    -0.14
    POSITIVE LOGITS
    ･･
    0.26
    ãģĤãĤĬãģĮ
    0.21
    ãĥ»ãĥ»ãĥ»↵↵
    0.21
    çĦ¡ãģĹãģ
    0.14
     ãĥ»
    0.13
    ãĢĢ
    0.11
    ķãĤĵ
    0.11
    ãĥ»ãĥ»
    0.11
    ãģĵãĤĵãģ«
    0.11
    .jp
    0.09
    Activations Density 0.139%

    No Known Activations