© 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. 337
    Prev
    Next
    INDEX
    Explanations

    register access, byte values

    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
    INET
    -0.12
    abet
    -0.11
    UUID
    -0.10
    ount
    -0.10
     STDOUT
    -0.10
     Yours
    -0.10
     Camel
    -0.10
    ica
    -0.10
     PATH
    -0.09
    nth
    -0.09
    POSITIVE LOGITS
     unused
    0.10
     Unused
    0.09
     bus
    0.09
     occupation
    0.09
     occupancy
    0.09
     sixteen
    0.09
     bits
    0.08
    loff
    0.08
     zeros
    0.08
    zt
    0.08
    Activations Density 0.993%

    No Known Activations