© 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. 545
    Prev
    Next
    INDEX
    Explanations

    vary depending

    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
    (SC
    -0.10
    lict
    -0.10
    lut
    -0.09
    esteem
    -0.09
    imension
    -0.09
     disfr
    -0.09
    emento
    -0.09
    fait
    -0.09
     immediately
    -0.09
    	then
    -0.09
    POSITIVE LOGITS
     depending
    0.31
     different
    0.27
     varying
    0.26
     varies
    0.23
     vary
    0.23
    depending
    0.23
     Depending
    0.23
     differing
    0.22
    Depending
    0.21
    different
    0.21
    Activations Density 2.457%

    No Known Activations