© 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. 21093
    Prev
    Next
    INDEX
    Explanations

    successfully executed

    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
     tack
    -0.06
    é£İåIJ¹
    -0.06
    ound
    -0.06
    isons
    -0.06
    ounds
    -0.06
    ston
    -0.06
    lse
    -0.06
    嵩
    -0.06
     ли
    -0.06
    umps
    -0.06
    POSITIVE LOGITS
     freue
    0.05
    åĨįæĢİä¹Ī
    0.05
    ä¸į失
    0.05
    çĽ¸å¯¹åºĶçļĦ
    0.05
     fortunately
    0.05
     lives
    0.05
    ä¸įæ¯Ķ
    0.05
     cint
    0.05
     mili
    0.05
     ocul
    0.05
    Activations Density 0.006%

    No Known Activations