© 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. 19785
    Prev
    Next
    INDEX
    Explanations

    degree, vertices, in, stimulation, starts, injury

    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
    便åĪ©
    -0.06
    otten
    -0.06
    otas
    -0.06
    ukkan
    -0.06
    âĢ¦it
    -0.06
     -:
    -0.06
    æıĴèĬ±
    -0.06
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    -0.05
    gara
    -0.05
    phu
    -0.05
    POSITIVE LOGITS
    ader
    0.06
    ench
    0.06
     Pera
    0.05
     pal
    0.05
     stuff
    0.05
    chema
    0.05
    iny
    0.05
    Ap
    0.05
    建平
    0.05
     urgently
    0.05
    Activations Density 0.002%

    No Known Activations