© 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. 16987
    Prev
    Next
    INDEX
    Explanations

    not enabled or available

    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
    rik
    -0.07
    rooms
    -0.06
    ered
    -0.06
    è¦ģæ±Ĥåľ¨
    -0.06
    rix
    -0.06
    tori
    -0.05
    æĪĸåľ¨
    -0.05
    è®°
    -0.05
    ommen
    -0.05
    åį«
    -0.05
    POSITIVE LOGITS
     îÈĻi
    0.05
     link
    0.05
    isle
    0.05
    ãģ«ãģ¤ãģªãģĮ
    0.05
    fast
    0.05
    link
    0.05
    åIJĮéģĵ
    0.05
    è¿Ļéĥ½æĺ¯
    0.05
    çŃīçŃī
    0.05
     Meld
    0.05
    Activations Density 0.019%

    No Known Activations