© 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. 2433
    Prev
    Next
    INDEX
    Explanations

    connecting to other

    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
    ares
    -0.09
    ès
    -0.08
    åĪ¶
    -0.08
     Entire
    -0.08
    ãĤ¦
    -0.08
     Coff
    -0.08
     cyclic
    -0.08
     accompany
    -0.07
     Boat
    -0.07
    ue
    -0.07
    POSITIVE LOGITS
     insertion
    0.11
     tys
    0.10
     derp
    0.10
    /from
    0.10
     via
    0.09
     rest
    0.09
    oS
    0.09
    iel
    0.09
     Burr
    0.09
    ап
    0.08
    Activations Density 0.259%

    No Known Activations