© 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. 2745
    Prev
    Next
    INDEX
    Explanations

    hair loss or styling

    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
     Deg
    -0.09
    able
    -0.08
    ç´
    -0.07
     Casa
    -0.07
    ering
    -0.07
    oga
    -0.06
     const
    -0.06
     DEBUG
    -0.06
     bir
    -0.06
    ign
    -0.06
    POSITIVE LOGITS
     follic
    0.18
    -haired
    0.14
    hair
    0.14
     shaft
    0.13
    Hair
    0.13
     Shaft
    0.13
     haired
    0.12
     Hair
    0.12
     shampoo
    0.12
     hair
    0.12
    Activations Density 0.174%

    No Known Activations