© 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. 20393
    Prev
    Next
    INDEX
    Explanations

    symbols and subsequent words

    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
     Dice
    -0.06
    çªŁ
    -0.05
    çľ¼
    -0.05
    çħ§
    -0.05
     dated
    -0.05
    zed
    -0.05
    -dashboard
    -0.05
     rel
    -0.05
    åĬ«
    -0.05
    æī§è¡Į人
    -0.05
    POSITIVE LOGITS
    بÙĪØ·
    0.06
    æĬĬè¿ĻäºĽ
    0.06
    æĬĬæīĢæľīçļĦ
    0.06
    å°Ĩè¿ĻäºĽ
    0.06
    ±
    0.06
    让è¿ĻäºĽ
    0.06
    ç¬ĥ
    0.05
    arth
    0.05
    boll
    0.05
    -ignore
    0.05
    Activations Density 0.001%

    No Known Activations