© 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. 1386
    Prev
    Next
    INDEX
    Explanations

    License terms

    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
     lingerie
    -0.39
    娱ä¹IJåľº
    -0.36
     démarch
    -0.33
    à¸Ľà¸£à¸°à¹Ģม
    -0.33
    åĭł
    -0.32
    娱ä¹IJå¹³åı°
    -0.32
     vidéos
    -0.32
     INCLUDED
    -0.31
     enthus
    -0.30
     prive
    -0.30
    POSITIVE LOGITS
    /legal
    0.42
    /lic
    0.41
    /↵↵↵↵
    0.40
     relent
    0.40
     misunder
    0.39
     disadv
    0.36
    ".↵↵↵↵
    0.36
     burge
    0.35
     unfavor
    0.35
     cuckold
    0.34
    Activations Density 6.994%

    No Known Activations