© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16952
    Prev
    Next
    INDEX
    Explanations

    hands, arms, or guns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    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
    éb
    -0.06
    jas
    -0.05
     eb
    -0.05
    Ñģни
    -0.05
    ä»İä¸Ĭ
    -0.05
    jad
    -0.05
     enfrent
    -0.05
    æĭIJ
    -0.05
    ãģĻãĤĬ
    -0.05
    رد
    -0.05
    POSITIVE LOGITS
    åľ¨ç»Ļ
    0.07
    uries
    0.06
    ugio
    0.06
    ä¾ĿçĦ¶åľ¨
    0.06
    aksin
    0.06
    kod
    0.05
     pensé
    0.05
    rary
    0.05
    èĪĪ
    0.05
     Chinh
    0.05
    Activations Density 0.001%

    No Known Activations