© 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. 54361
    Prev
    Next
    INDEX
    Explanations

    cosmetic surgery

    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
    TRL
    -0.08
     processing
    -0.07
     narc
    -0.07
    fac
    -0.07
    ç«
    -0.07
     Sap
    -0.07
     depress
    -0.07
    -se
    -0.07
    ign
    -0.07
    newline
    -0.07
    POSITIVE LOGITS
     Hidden
    0.11
     Sacr
    0.10
    meld
    0.10
     incap
    0.09
     skl
    0.09
    udas
    0.09
     Voices
    0.09
    chia
    0.09
     Followers
    0.09
     comple
    0.09
    Activations Density 0.015%

    No Known Activations