© 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. 56418
    Prev
    Next
    INDEX
    Explanations

    religious/ethnic prejudice

    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
     conf
    -0.09
    ESH
    -0.09
     Fly
    -0.08
     DJ
    -0.08
    alian
    -0.08
     delt
    -0.08
     spin
    -0.08
     Conf
    -0.08
     Stations
    -0.08
     cont
    -0.08
    POSITIVE LOGITS
    gard
    0.10
    ecz
    0.09
     fif
    0.09
    outube
    0.09
    igli
    0.08
    -append
    0.08
     moss
    0.08
    _snd
    0.08
    adt
    0.08
     spare
    0.08
    Activations Density 0.010%

    No Known Activations