© 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. 20153
    Prev
    Next
    INDEX
    Explanations

    Merb, singleton, laparoscopic, Netbook, Resin, schizo, PVM

    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
    çĨĦ
    -0.06
    roda
    -0.06
    avance
    -0.06
    ely
    -0.06
    own
    -0.05
    è®®
    -0.05
    äºĮ人
    -0.05
    rego
    -0.05
    âĹİ
    -0.05
    iw
    -0.05
    POSITIVE LOGITS
    åľ¨éĩĮéĿ¢
    0.06
    å´Ń
    0.06
    bel
    0.06
    δά
    0.06
    yn
    0.05
     reverse
    0.05
     mur
    0.05
    åħ¶ä¸ŃçļĦ
    0.05
     Belg
    0.05
    ยà¹īà¸Ńà¸Ļ
    0.05
    Activations Density 0.047%

    No Known Activations