© 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. 2424
    Prev
    Next
    INDEX
    Explanations

    in re

    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
     Tenn
    -0.08
     Exhaust
    -0.07
     Emit
    -0.07
    utch
    -0.07
    ang
    -0.07
    Applied
    -0.07
    anga
    -0.06
    vi
    -0.06
     vanilla
    -0.06
     Su
    -0.06
    POSITIVE LOGITS
    eor
    0.11
    .Pin
    0.11
    dana
    0.11
    @c
    0.11
    oload
    0.11
    iterr
    0.10
    toi
    0.10
    =~
    0.10
    /Branch
    0.10
    pring
    0.10
    Activations Density 0.045%

    No Known Activations