© 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. 20881
    Prev
    Next
    INDEX
    Explanations

    **Declaring variables and their types**

    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
    erner
    -0.07
    大çIJĨ
    -0.06
    å·¥ä½ľæĪĸ
    -0.05
    åĨ¶
    -0.05
    ernal
    -0.05
    éĩijå±ŀæĿIJæĸĻ
    -0.05
    pes
    -0.05
     digest
    -0.05
    REEN
    -0.05
    POOL
    -0.05
    POSITIVE LOGITS
    kip
    0.07
    .nih
    0.06
    fully
    0.06
    ìĦľëĬĶ
    0.05
    åħ¶å¯¹
    0.05
    ALLY
    0.05
    asc
    0.05
    keb
    0.05
    inally
    0.05
    uhe
    0.05
    Activations Density 0.015%

    No Known Activations