© 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. 678
    Prev
    Next
    INDEX
    Explanations

    into phrases

    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
    ify
    -0.10
    ìķĦ
    -0.08
    rip
    -0.08
    ½
    -0.08
    enstein
    -0.08
    æĴ
    -0.08
    ENT
    -0.08
    ister
    -0.08
    ford
    -0.08
     leap
    -0.08
    POSITIVE LOGITS
    /out
    0.21
    /from
    0.15
     obliv
    0.14
     adulthood
    0.12
     account
    0.12
    ductory
    0.11
     harms
    0.11
    prising
    0.11
     consideration
    0.11
    action
    0.11
    Activations Density 0.398%

    No Known Activations