© 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. 56410
    Prev
    Next
    INDEX
    Explanations

    harm, offensive, or illegal actions

    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
    osti
    -0.10
    ourg
    -0.10
    mons
    -0.10
     rede
    -0.10
    stein
    -0.09
    idon
    -0.09
    [at
    -0.09
     å¼Ģ
    -0.09
    åŃĺåľ¨
    -0.09
    /raw
    -0.09
    POSITIVE LOGITS
     Harm
    0.09
    arak
    0.08
    Assembly
    0.08
     dow
    0.08
     confort
    0.07
     comfort
    0.07
    arna
    0.07
    oke
    0.07
     knowingly
    0.07
     unnecessarily
    0.07
    Activations Density 0.020%

    No Known Activations