© 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. 1630
    Prev
    Next
    INDEX
    Explanations

    ization

    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
    (es
    -0.12
    (s
    -0.11
    /features
    -0.10
    /method
    -0.10
    ëĵ¤
    -0.10
    åı¸
    -0.10
    AMILY
    -0.10
    å°Ķ
    -0.10
    vider
    -0.09
     maker
    -0.09
    POSITIVE LOGITS
     efforts
    0.15
     process
    0.14
     occurs
    0.14
    åĻ¨
    0.14
     techniques
    0.13
    /rec
    0.13
    /storage
    0.13
    /edit
    0.12
     done
    0.12
     occurring
    0.11
    Activations Density 3.282%

    No Known Activations