© 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. 39
    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
    ossip
    -0.23
    école
    -0.23
    åİĿ
    -0.22
    houette
    -0.21
     (
    -0.21
     jMenuItem
    -0.21
    "label
    -0.21
    privation
    -0.21
    "default
    -0.21
    ackbar
    -0.20
    POSITIVE LOGITS
     Erotic
    0.32
     Wrest
    0.31
     Prostit
    0.29
     Interracial
    0.27
     sublicense
    0.27
    )((((
    0.27
     misunder
    0.25
    讹
    0.25
     Hannity
    0.23
    -Semit
    0.23
    Activations Density 0.116%

    No Known Activations