© 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
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3199
    Prev
    Next
    INDEX
    Explanations

    How to, how do, is there

    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
     pun
    -0.10
     Lear
    -0.10
    /errors
    -0.09
     elect
    -0.09
    osis
    -0.09
    ussion
    -0.09
     Zus
    -0.08
    leich
    -0.08
    ije
    -0.08
    /basic
    -0.08
    POSITIVE LOGITS
     recommend
    0.08
    (*(
    0.08
     Monaco
    0.08
     chances
    0.08
     monkey
    0.08
     recommends
    0.07
     approve
    0.07
    iry
    0.07
    rap
    0.07
    iki
    0.07
    Activations Density 0.740%

    No Known Activations