© 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. 19342
    Prev
    Next
    INDEX
    Explanations

    UNIX command

    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
    åĽ½æľīèµĦ产
    -0.05
    BY
    -0.05
    borough
    -0.05
    urut
    -0.05
    TTY
    -0.05
    è¾ij
    -0.05
    çĸ¹
    -0.05
    regist
    -0.05
    çĶŁåij½å®īåħ¨
    -0.05
     N
    -0.05
    POSITIVE LOGITS
    æµĵ缩
    0.06
     =>$
    0.06
    дÑı
    0.06
    +self
    0.06
    utter
    0.06
    ä¼ĺåĬ¿
    0.06
     Forn
    0.06
    (QL
    0.05
    ekl
    0.05
    atore
    0.05
    Activations Density 0.001%

    No Known Activations