© 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. 898
    Prev
    Next
    INDEX
    Explanations

    would like

    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
    cox
    -0.09
     often
    -0.09
    iber
    -0.08
     oft
    -0.08
    ando
    -0.08
    aren
    -0.08
    WORD
    -0.08
     sometimes
    -0.08
    amba
    -0.08
     Cox
    -0.08
    POSITIVE LOGITS
    nt
    0.18
     conce
    0.13
     hypoth
    0.13
    -be
    0.13
     otherwise
    0.12
    nts
    0.12
     ideally
    0.11
    ’ve
    0.11
     sooner
    0.11
     conceivable
    0.11
    Activations Density 0.664%

    No Known Activations