© 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. 20477
    Prev
    Next
    INDEX
    Explanations

    form a statement

    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
    iar
    -0.06
    çĴIJ
    -0.05
    è½
    -0.05
    žu
    -0.05
    çŃī级
    -0.05
    æľīå¾Ī强çļĦ
    -0.05
    ä½İä½į
    -0.05
    Ú©ÙĪر
    -0.05
     indu
    -0.05
    ","",
    -0.05
    POSITIVE LOGITS
    rack
    0.06
    éļıè¡Į
    0.06
    ä¸įå½±åĵį
    0.06
    è¿Ļéĥ¨
    0.05
     guise
    0.05
    ACITY
    0.05
    idata
    0.05
    Ease
    0.05
    hoe
    0.05
    åħ±çĶŁ
    0.05
    Activations Density 0.013%

    No Known Activations