© 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. 402
    Prev
    Next
    INDEX
    Explanations

    how something is done

    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
     quite
    -0.10
     noticeably
    -0.09
     only
    -0.09
     reminder
    -0.09
     ~=
    -0.09
     diz
    -0.08
     modest
    -0.08
     moderately
    -0.08
    ummer
    -0.08
     acknowledgement
    -0.08
    POSITIVE LOGITS
    /how
    0.18
    /if
    0.13
     whereabouts
    0.13
     exact
    0.11
     accurately
    0.11
     exactly
    0.11
     beforehand
    0.11
     behavior
    0.11
    —who
    0.10
     specific
    0.10
    Activations Density 3.439%

    No Known Activations