© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17054
    Prev
    Next
    INDEX
    Explanations

    that of

    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
    æĢ§åľ°
    -0.07
    oscop
    -0.06
    abri
    -0.06
    entially
    -0.06
    ä¹ĭéĹ´
    -0.06
    èŁ
    -0.06
    æĢ§åıĬ
    -0.06
    inkin
    -0.06
    ä¹ĭéĸĵ
    -0.06
    éĿłè¿ij
    -0.05
    POSITIVE LOGITS
    æł·çļĦ
    0.06
     varying
    0.06
    vary
    0.06
     Heard
    0.05
    Ø©
    0.05
    age
    0.05
    ation
    0.05
    ست
    0.05
    any
    0.05
     ranging
    0.05
    Activations Density 0.033%

    No Known Activations