© 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. 56064
    Prev
    Next
    INDEX
    Explanations

    successful professional new organic large practical routine

    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
     mish
    -0.09
    aub
    -0.07
     strictly
    -0.07
    ivr
    -0.07
    xEF
    -0.07
    urrect
    -0.06
    chants
    -0.06
    _corner
    -0.06
    vang
    -0.06
     drift
    -0.06
    POSITIVE LOGITS
    erah
    0.11
    ieten
    0.10
    bos
    0.09
     Aluminium
    0.09
    cdc
    0.09
    gard
    0.09
    ein
    0.09
    amd
    0.09
    .optional
    0.09
    dfd
    0.09
    Activations Density 0.145%

    No Known Activations