© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 196
    Prev
    Next
    INDEX
    Explanations

    states, expectations, or developments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ§ãĤĤ
    -0.11
    ãģĹãģĭãģĹ
    -0.10
    ãģĹãģĭ
    -0.10
    ĵĺ
    -0.09
     documented
    -0.09
    ãģĿãģĹãģ¦
    -0.08
    ãģĵãĤĵ
    -0.08
     couch
    -0.08
     crit
    -0.08
     foundational
    -0.08
    POSITIVE LOGITS
     âĢ»
    0.16
    âij
    0.16
    âĢ»
    0.15
    ãĥ»
    0.15
    _flg
    0.15
    ãĥ»ãĥ»ãĥ»↵↵
    0.15
    ãĢĢ
    0.14
    âĻª↵↵
    0.14
    ãģĤãĤĬãģĮ
    0.14
    ･･
    0.13
    Activations Density 3.251%

    No Known Activations