© 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. 4459
    Prev
    Next
    INDEX
    Explanations

    impediment, obstruction, hinder

    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
    dest
    -0.10
    /fa
    -0.09
     bab
    -0.09
    anzi
    -0.09
     INV
    -0.08
    izio
    -0.08
     deco
    -0.08
     cro
    -0.08
    (Locale
    -0.08
    leh
    -0.08
    POSITIVE LOGITS
     hinder
    0.17
     obstacle
    0.17
     hind
    0.17
     imped
    0.16
     obstruct
    0.15
     obstruction
    0.13
     Hindered
    0.12
     obstacles
    0.12
     Hind
    0.12
     Freedom
    0.11
    Activations Density 0.204%

    No Known Activations