© 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. 2002
    Prev
    Next
    INDEX
    Explanations

    medical/technical terms

    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
    ãĥ
    -0.08
    Guest
    -0.07
     nud
    -0.07
    ject
    -0.07
    ahi
    -0.07
     Dick
    -0.07
     Guest
    -0.07
    ï¼īãĢģ
    -0.07
    wer
    -0.07
     immediately
    -0.07
    POSITIVE LOGITS
    —all
    0.21
     etc
    0.21
    etc
    0.16
     none
    0.14
    (all
    0.13
    -all
    0.13
     miscellaneous
    0.12
     ëĵ±
    0.12
     all
    0.12
     finally
    0.11
    Activations Density 2.919%

    No Known Activations