© 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. 1876
    Prev
    Next
    INDEX
    Explanations

    parenthetical explanations

    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
    ankind
    -0.09
    instead
    -0.09
    blah
    -0.09
    intr
    -0.08
     Trouble
    -0.08
     miscellaneous
    -0.08
    eacher
    -0.08
    INS
    -0.08
    asma
    -0.08
    etc
    -0.08
    POSITIVE LOGITS
     admittedly
    0.16
     note
    0.15
     actually
    0.14
     btw
    0.14
     later
    0.13
     technically
    0.13
     caveat
    0.12
     siden
    0.12
     also
    0.12
     Note
    0.11
    Activations Density 1.385%

    No Known Activations