© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19446
    Prev
    Next
    INDEX
    Explanations

    multi-word phrases

    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
    ugi
    -0.06
    zwischen
    -0.06
     hil
    -0.06
    jev
    -0.06
    jsc
    -0.06
    igkeiten
    -0.06
    å¦ĤæŀľæĤ¨æĺ¯
    -0.05
    åīªåĪĢ
    -0.05
    ÙĪÙĨ
    -0.05
    iaÅĤa
    -0.05
    POSITIVE LOGITS
    ting
    0.06
    ÑĤÑĥ
    0.06
    -ext
    0.06
     verlo
    0.05
    ancier
    0.05
     whilst
    0.05
    estre
    0.05
     Whilst
    0.05
    ter
    0.05
    неÑĤа
    0.05
    Activations Density 0.041%

    No Known Activations