© 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. 17208
    Prev
    Next
    INDEX
    Explanations

    morphological and linguistic features

    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
    ysi
    -0.06
     boo
    -0.06
     ‘’
    -0.06
    çIJ¦
    -0.06
     استث
    -0.06
    inx
    -0.06
    strained
    -0.06
     Hindered
    -0.06
    ellet
    -0.06
     Diag
    -0.06
    POSITIVE LOGITS
     encode
    0.06
    åijIJ
    0.05
     dearly
    0.05
     Prec
    0.05
     vend
    0.05
     geli
    0.05
    ç²¾
    0.05
    çī²çķľ
    0.05
    åĶ¯ä¸Ģ
    0.05
    orientation
    0.05
    Activations Density 0.013%

    No Known Activations