© 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. 391
    Prev
    Next
    INDEX
    Explanations

    difficulty

    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
    bió
    -0.26
     massaggi
    -0.24
    ancellable
    -0.22
    .maxLength
    -0.22
    portun
    -0.21
    thinkable
    -0.20
    galement
    -0.20
    nü
    -0.20
    iams
    -0.20
    CGColor
    -0.20
    POSITIVE LOGITS
    åĽ°éļ¾
    0.28
    æī¾åĪ°
    0.26
     Difficulty
    0.25
    æľĢéļ¾
    0.25
    åĽ°
    0.24
    åħĭæľį
    0.24
     unsuccessfully
    0.24
     getSupportActionBar
    0.23
    æĪIJåĬŁçļĦ
    0.23
     find
    0.23
    Activations Density 2.732%

    No Known Activations