© 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. 22215
    Prev
    Next
    INDEX
    Explanations

    dress code and attire

    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
    è¿ĻäºĽå°ı
    -0.06
     tract
    -0.06
     zab
    -0.06
    è¿ĻäºĽè¯Ŀ
    -0.06
    çļĦæīĭæ³ķ
    -0.06
    éŁ
    -0.06
    VOKE
    -0.05
    accio
    -0.05
    ring
    -0.05
    liwe
    -0.05
    POSITIVE LOGITS
    ä¸įæĺİ
    0.06
    éģµ
    0.06
    代表çļĦ
    0.05
     conlle
    0.05
     cons
    0.05
    forms
    0.05
    åij½ä»¤
    0.05
    è§Ĥ
    0.05
    ono
    0.05
    åħ·ä½ĵè¦ģæ±Ĥ
    0.05
    Activations Density 0.007%

    No Known Activations