© 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. 16924
    Prev
    Next
    INDEX
    Explanations

    industry and uses

    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
    ieni
    -0.06
     fung
    -0.06
    åľ¨è¿Ļä¸Ģ
    -0.06
    补缺
    -0.06
     cred
    -0.06
    æĿĥéĩį
    -0.06
    ellipsis
    -0.05
    ernen
    -0.05
    解éĩĬæĿĥ
    -0.05
    klang
    -0.05
    POSITIVE LOGITS
    abi
    0.06
     Citation
    0.05
     اÙĨØ·ÙĦاÙĤ
    0.05
    åĴ
    0.05
     abundant
    0.05
    man
    0.05
     persecuted
    0.05
     Dame
    0.05
    ìļ©
    0.05
    bor
    0.05
    Activations Density 0.138%

    No Known Activations