© 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. 529
    Prev
    Next
    INDEX
    Explanations

    have/had been

    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
     having
    -0.10
     have
    -0.09
    variably
    -0.08
     Have
    -0.08
     ayant
    -0.08
    Have
    -0.08
     knew
    -0.08
     HAVE
    -0.08
     embody
    -0.08
    è¿ĺ
    -0.07
    POSITIVE LOGITS
     been
    0.32
    been
    0.23
     Been
    0.21
     BEEN
    0.20
    htag
    0.19
     become
    0.19
    htable
    0.19
    nt
    0.18
    Been
    0.18
    htags
    0.17
    Activations Density 0.809%

    No Known Activations