© 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. 2061
    Prev
    Next
    INDEX
    Explanations

    ambiguous, conflicted, mixed, controversial

    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
    kke
    -0.09
    atos
    -0.09
    urve
    -0.09
     unimagin
    -0.09
    occer
    -0.09
    /library
    -0.09
     variety
    -0.08
     imaginable
    -0.08
    isation
    -0.08
    afs
    -0.08
    POSITIVE LOGITS
     blessing
    0.10
     Cond
    0.10
     Pry
    0.10
     edged
    0.09
    adel
    0.09
     doubtful
    0.09
    -ed
    0.09
     ambiguous
    0.09
     controversial
    0.08
     gord
    0.08
    Activations Density 0.199%

    No Known Activations