© 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. 4137
    Prev
    Next
    INDEX
    Explanations

    handsome man names

    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
     herself
    -0.17
    /he
    -0.17
     latina
    -0.11
     Latina
    -0.10
     vagina
    -0.10
    esh
    -0.10
     womb
    -0.10
    ikh
    -0.10
     gigg
    -0.10
    .cc
    -0.10
    POSITIVE LOGITS
     handsome
    0.13
     himself
    0.13
     коÑĤоÑĢÑĭй
    0.13
     masculinity
    0.12
    fts
    0.11
     bachelor
    0.11
     misogyn
    0.11
     proposing
    0.10
     sexist
    0.10
    ft
    0.10
    Activations Density 0.330%

    No Known Activations