© 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. 20297
    Prev
    Next
    INDEX
    Explanations

    Forwarded by names

    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
    oci
    -0.06
    òm
    -0.06
    contr
    -0.06
    سر
    -0.06
    èĬĤ
    -0.06
    orz
    -0.06
    æĸŃäºĨ
    -0.06
    oes
    -0.06
    æĺ¯æ°´
    -0.05
     اÛĮÙĨÚ©Ùĩ
    -0.05
    POSITIVE LOGITS
    Ø®
    0.06
    earable
    0.05
    åĪģ
    0.05
    -transparent
    0.05
    hill
    0.05
    nip
    0.05
    åĩĨ
    0.05
    ä¼ij
    0.05
     ()=>
    0.05
    '}
    0.05
    Activations Density 0.013%

    No Known Activations