© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1073
    Prev
    Next
    INDEX
    Explanations

    P

    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
    ickerView
    -0.36
    oulos
    -0.29
    aternity
    -0.27
    ponce
    -0.27
    enance
    -0.27
    ipel
    -0.26
    uyá»ĥn
    -0.26
    akistan
    -0.25
    QRSTUV
    -0.24
    irates
    -0.24
    POSITIVE LOGITS
    innacle
    0.49
    egasus
    0.43
    ICTURE
    0.40
    ÑĥниÑĨип
    0.34
     огÑĢомн
    0.33
    ritch
    0.33
    malink
    0.33
    CLUDING
    0.31
    entiful
    0.30
    对çħ§æ£ĢæŁ¥
    0.30
    Activations Density 6.357%

    No Known Activations