© 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. 21742
    Prev
    Next
    INDEX
    Explanations

    channel connecting

    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
    colo
    -0.06
    å·¥ä½ľä½ľé£İ
    -0.05
    度ãģª
    -0.05
    建çŃij设计
    -0.05
     bÃło
    -0.05
    å¿«è¦ģ
    -0.05
    reich
    -0.05
    è§Ĵ度æĿ¥è¯´
    -0.05
    èĵĸ
    -0.05
    anc
    -0.05
    POSITIVE LOGITS
    IMS
    0.06
    eranno
    0.06
    secured
    0.06
    LOT
    0.06
     secure
    0.06
    uent
    0.06
    çĦķ
    0.06
    ave
    0.06
    ä¿Ŀå¯Ĩ
    0.06
    é¹Ń
    0.06
    Activations Density 0.002%

    No Known Activations