© 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. 55276
    Prev
    Next
    INDEX
    Explanations

    naming and renaming places and 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
    orgeous
    -0.11
    .sigmoid
    -0.10
    olid
    -0.10
    å¾Ħ
    -0.10
    ione
    -0.09
    اب
    -0.09
    Depending
    -0.09
     spread
    -0.09
    cc
    -0.09
     tér
    -0.09
    POSITIVE LOGITS
     naming
    0.12
     renaming
    0.12
     Naming
    0.11
    Naming
    0.10
     prefixes
    0.10
     alphanumeric
    0.09
     Rename
    0.08
     vanity
    0.08
     rename
    0.08
     tou
    0.08
    Activations Density 0.067%

    No Known Activations