© 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. 1824
    Prev
    Next
    INDEX
    Explanations

    female terms

    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
     himself
    -0.22
     koji
    -0.18
    /she
    -0.18
     handsome
    -0.18
     коÑĤоÑĢÑĭй
    -0.17
     Jr
    -0.17
     Himself
    -0.16
    /her
    -0.14
     français
    -0.13
    álido
    -0.13
    POSITIVE LOGITS
     herself
    0.38
    /he
    0.23
     pregnancy
    0.17
     breasts
    0.16
     Latina
    0.16
    pher
    0.16
    editary
    0.15
     husband
    0.15
    athed
    0.15
     pregnant
    0.15
    Activations Density 2.660%

    No Known Activations