© 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. 19131
    Prev
    Next
    INDEX
    Explanations

    **else then block introducer**

    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¸į以
    -0.05
    uert
    -0.05
    altet
    -0.05
    atty
    -0.05
    ivo
    -0.05
    éĻ¤éĿŀ
    -0.05
    eria
    -0.05
     pity
    -0.05
    oked
    -0.05
    åij¼
    -0.05
    POSITIVE LOGITS
    cik
    0.06
    EI
    0.06
    estik
    0.06
    èĥ
    0.06
    æ°Ĺãģ«åħ¥ãĤĬãģ®
    0.06
    akarta
    0.06
    ?>>
    0.06
    æĽ¼èģĶ
    0.06
    cich
    0.06
    Emb
    0.06
    Activations Density 0.002%

    No Known Activations