© 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. 19325
    Prev
    Next
    INDEX
    Explanations

    body parts and features

    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
    baik
    -0.06
    hhh
    -0.05
     ÑģебÑı
    -0.05
    åĬ³
    -0.05
    åįıä¼ļä¼ļéķ¿
    -0.05
    å¤ļ
    -0.05
    quisite
    -0.05
    osl
    -0.05
    æĿIJ
    -0.05
    åĪĻçĶ±
    -0.05
    POSITIVE LOGITS
    natur
    0.06
    amedi
    0.06
    çŁ¥è¯ĨéĿ¢
    0.06
    溯
    0.06
     Bestimm
    0.05
    боÑĢÑĥ
    0.05
    edr
    0.05
     нео
    0.05
    rien
    0.05
    nex
    0.05
    Activations Density 0.001%

    No Known Activations