© 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. 18753
    Prev
    Next
    INDEX
    Explanations

    are there any

    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
    kut
    -0.06
    ubs
    -0.06
    à¹Ĩ
    -0.05
    沫
    -0.05
    chk
    -0.05
    ings
    -0.05
    ingly
    -0.05
    rana
    -0.05
     ANY
    -0.05
    اء
    -0.05
    POSITIVE LOGITS
     ervan
    0.06
    RH
    0.06
    以æ¡Ī
    0.06
    ä¸įåı¯
    0.06
    ightly
    0.05
    ï¼Ī
    0.05
    Mich
    0.05
    жеÑĤÑģÑı
    0.05
    à¸¹à¸Ľ
    0.05
    大ä¼ļ
    0.05
    Activations Density 0.008%

    No Known Activations