© 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. 56702
    Prev
    Next
    INDEX
    Explanations

    portable electronic devices

    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
     prov
    -0.09
     wheels
    -0.08
    eren
    -0.08
    icer
    -0.08
     taps
    -0.08
     tap
    -0.07
     Pir
    -0.07
     contrib
    -0.07
    sd
    -0.07
     Werner
    -0.07
    POSITIVE LOGITS
     ambit
    0.11
     Mand
    0.10
     fanc
    0.10
     cerv
    0.10
     Soul
    0.10
     relax
    0.10
    0.10
    ivi
    0.10
    lero
    0.10
     mul
    0.10
    Activations Density 0.069%

    No Known Activations