© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3638
    Prev
    Next
    INDEX
    Explanations

    reason for the

    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
    apore
    -0.10
    (as
    -0.09
    tru
    -0.08
    iku
    -0.08
     hor
    -0.07
     Haram
    -0.07
    soever
    -0.07
     brow
    -0.07
     otherwise
    -0.07
     Emerson
    -0.07
    POSITIVE LOGITS
     latter
    0.14
    (fabs
    0.09
    ufe
    0.08
    rok
    0.08
    abin
    0.08
    lob
    0.08
    angler
    0.08
    ...)↵↵
    0.08
     ]).
    0.08
    &o
    0.08
    Activations Density 0.278%

    No Known Activations