© 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
    2. Olmo-3-1025-7B
    3. 16-RES-MATRYOSHKA-65K
    4. 1484
    Prev
    Next
    INDEX
    Explanations

    list of things

    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
    }}>
    -0.14
     bevor
    -0.13
    +='
    -0.13
    ());//
    -0.13
    '],'
    -0.13
    )|(
    -0.12
     ».
    -0.12
     )]↵
    -0.12
    ':['
    -0.12
    )↵↵↵↵↵↵↵↵
    -0.12
    POSITIVE LOGITS
     etc
    0.19
     ëĵ±
    0.12
    çŃī
    0.10
    ,
    0.09
    ,and
    0.09
     &
    0.08
     ect
    0.08
     and
    0.08
    etc
    0.07
    (optional
    0.07
    Activations Density 1.262%

    No Known Activations