© 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. 19825
    Prev
    Next
    INDEX
    Explanations

    ```textC++ include statements```

    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
    uling
    -0.06
    alp
    -0.06
    ablement
    -0.06
    ÑģÑĤÑĢÑı
    -0.06
    agment
    -0.06
    odor
    -0.06
    سازÛĮ
    -0.06
    elts
    -0.06
    angi
    -0.06
    klin
    -0.06
    POSITIVE LOGITS
    iaux
    0.06
    iral
    0.05
    YP
    0.05
    åı¸éķ¿
    0.05
    ä¸ĵçĶ¨
    0.05
    å®ı大
    0.05
    ocking
    0.05
    arks
    0.05
    itic
    0.05
     εγκ
    0.05
    Activations Density 0.004%

    No Known Activations