© 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. 18824
    Prev
    Next
    INDEX
    Explanations

    directly activated

    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
    ä¸Ģç¬Ķ
    -0.06
    éħįç½®æĸ¹éĿ¢
    -0.05
    ä¸įä¿¡
    -0.05
    çĶŁç´ł
    -0.05
    rei
    -0.05
    atória
    -0.05
    ת×Ļ
    -0.05
    utting
    -0.05
    DEN
    -0.05
    伤害
    -0.05
    POSITIVE LOGITS
    äºİä»Ĭå¹´
    0.06
    ugh
    0.06
    veno
    0.06
    quet
    0.05
    渴
    0.05
     bid
    0.05
    er
    0.05
    aturahmi
    0.05
    å¼łä¸ī
    0.05
     concept
    0.05
    Activations Density 0.322%

    No Known Activations