© 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. 21344
    Prev
    Next
    INDEX
    Explanations

    red colobus

    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
    æĦŁ
    -0.06
    æ´»
    -0.06
    é¢ĨåŁŁ
    -0.06
    çIJĨ
    -0.06
    gard
    -0.06
    çģµæ´»
    -0.06
    æĢĿç»´
    -0.05
    è§ģ
    -0.05
    æģ°æģ°
    -0.05
    -qu
    -0.05
    POSITIVE LOGITS
    çļĦä¸Ģ件
    0.06
    othi
    0.06
    ulée
    0.05
    åĨįçĤ¹åĩ»
    0.05
    çľ¼äºĨ
    0.05
    _HOOK
    0.05
    aukee
    0.05
     accol
    0.05
    å¹´äºĨ
    0.05
    enan
    0.05
    Activations Density 0.188%

    No Known Activations