© 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. 657
    Prev
    Next
    INDEX
    Explanations

    phrases often starting with 'for', 'fact', 'have', 'and', 'trying', 'I', 'decided', 'usually', 'looks', 'makes'

    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
     trous
    -0.14
     busty
    -0.12
     âĢķ
    -0.11
     grues
    -0.11
     quotid
    -0.11
     tatto
    -0.11
     “âĢ¦
    -0.10
     cupid
    -0.10
     Xxx
    -0.10
     âĢ¦↵↵
    -0.10
    POSITIVE LOGITS
     kinda
    0.16
     really
    0.16
     pretty
    0.15
     stuff
    0.13
     thing
    0.13
     guys
    0.13
    eee
    0.12
     sort
    0.12
     maybe
    0.12
     nice
    0.11
    Activations Density 4.685%

    No Known Activations