© 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. 19051
    Prev
    Next
    INDEX
    Explanations

    cooks

    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
    æŶåĢĻ
    -0.06
    дей
    -0.06
    ......
    -0.06
     ...,
    -0.05
    ...,
    -0.05
    缸åıį
    -0.05
    Ń
    -0.05
    ä¸įä»ħèĥ½å¤Ł
    -0.05
    âĢ¦,
    -0.05
    âĢ¦âĢ¦
    -0.05
    POSITIVE LOGITS
    ä¿¡æģ¯åıijå¸ĥ
    0.07
    ekat
    0.07
    ammo
    0.06
    ä¹Ŀ大
    0.06
    laubt
    0.06
     benne
    0.06
    ãģ£ãģ¡ãĤĬ
    0.06
    宿
    0.06
    è¦ģä½ł
    0.06
    hin
    0.06
    Activations Density 0.016%

    No Known Activations