© 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. 18013
    Prev
    Next
    INDEX
    Explanations

    ranking categories and levels

    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
    ä¸ĬæīĢ
    -0.07
    á»ijc
    -0.06
    ascal
    -0.06
    ä¾Ŀæ³ķ追究责任
    -0.06
    åħ¬æīĢ
    -0.06
     Badezimmer
    -0.06
    elis
    -0.05
     nurs
    -0.05
    æŬ
    -0.05
     invece
    -0.05
    POSITIVE LOGITS
    çĽĺ
    0.05
    æĭ¨
    0.05
    æ¾Ħ
    0.05
    åħ¶ä¸Ń
    0.05
    ze
    0.05
     ins
    0.05
     metam
    0.05
    ordered
    0.05
     san
    0.05
    erte
    0.05
    Activations Density 0.173%

    No Known Activations