© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20156
    Prev
    Next
    INDEX
    Explanations

    text following '+'

    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
     Brend
    -0.06
    ake
    -0.06
    ØŃÙĬ
    -0.06
    uite
    -0.05
    —at
    -0.05
    ÐĺС
    -0.05
    åIJijèį£
    -0.05
     *))
    -0.05
    weise
    -0.05
    estate
    -0.05
    POSITIVE LOGITS
     Daarnaast
    0.06
    ä¿¡ç®±
    0.06
    whel
    0.05
     оÑģÑĤ
    0.05
    ä¼ģä¸ļåIJĪä½ľ
    0.05
    Ú©Ûģ
    0.05
    继ç»ŃåĬªåĬĽ
    0.05
    éľ²éĿ¢
    0.05
    åĨįåĪ°
    0.05
    ण
    0.05
    Activations Density 0.020%

    No Known Activations