© 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. 20259
    Prev
    Next
    INDEX
    Explanations

    limitations

    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
    æĶ
    -0.06
    éŃĦ
    -0.06
    iously
    -0.06
    æ¶Ľ
    -0.06
    icted
    -0.05
     Locker
    -0.05
    fer
    -0.05
    .uk
    -0.05
    er
    -0.05
    ives
    -0.05
    POSITIVE LOGITS
    limitations
    0.07
    laat
    0.06
    rophe
    0.06
    hood
    0.06
    iqu
    0.06
     Reached
    0.06
    ocl
    0.06
    çļĦä»ĸ
    0.06
     polici
    0.06
    راÙĤ
    0.06
    Activations Density 0.005%

    No Known Activations