© 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. 18522
    Prev
    Next
    INDEX
    Explanations

    legal inheritance or capability

    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
    åı°
    -0.05
    å¢ĥçķĮ
    -0.05
    纳
    -0.05
    éĽ·é¸£
    -0.05
    åIJĦç±»
    -0.05
    å¥īçĮ®
    -0.05
    åIJĦç§į
    -0.05
     coordinate
    -0.05
     physical
    -0.05
    çī©çIJĨ
    -0.05
    POSITIVE LOGITS
    inqu
    0.07
    aderos
    0.06
     instruc
    0.06
    oble
    0.06
    æ¯ıå¼ł
    0.06
    _each
    0.06
    Detach
    0.06
    个个
    0.06
    غاÙĦ
    0.06
    æ¬ł
    0.05
    Activations Density 0.011%

    No Known Activations