© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1841
    Prev
    Next
    INDEX
    Explanations

    adult content

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MOTE
    -0.26
     ámbito
    -0.24
    黢
    -0.24
    avourites
    -0.24
    anoia
    -0.23
    нÑıÑĤие
    -0.23
    hipster
    -0.23
     Stateless
    -0.23
    isbury
    -0.23
    Verdana
    -0.23
    POSITIVE LOGITS
    rvine
    0.34
    uxtap
    0.33
     perpetr
    0.30
    isex
    0.26
     erotica
    0.26
    |unique
    0.26
     cuckold
    0.26
    llum
    0.25
    ormsg
    0.25
     bigot
    0.25
    Activations Density 6.448%

    No Known Activations