© 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. 2020
    Prev
    Next
    INDEX
    Explanations

    that it

    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
     ,$
    -0.10
    them
    -0.09
     him
    -0.08
     herself
    -0.08
     THEM
    -0.08
     placebo
    -0.07
     whose
    -0.07
    ecome
    -0.07
    agina
    -0.07
    èĢħ
    -0.07
    POSITIVE LOGITS
     there
    0.25
     it
    0.17
     neither
    0.16
     each
    0.15
    there
    0.15
    /how
    0.15
     these
    0.15
     they
    0.14
     certain
    0.14
     every
    0.13
    Activations Density 2.755%

    No Known Activations