© 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. 4205
    Prev
    Next
    INDEX
    Explanations

    This source file

    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
    SENS
    -0.10
    ou
    -0.10
    uit
    -0.09
    izr
    -0.09
     Erf
    -0.09
    onder
    -0.08
     iss
    -0.08
     grain
    -0.08
    rand
    -0.08
    611
    -0.08
    POSITIVE LOGITS
    anka
    0.09
     Tattoo
    0.08
     Tits
    0.08
     Lun
    0.08
     Ki
    0.08
    anga
    0.08
     Rage
    0.07
     Trophy
    0.07
    Wrapped
    0.07
     oma
    0.07
    Activations Density 0.137%

    No Known Activations