© 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. 17639
    Prev
    Next
    INDEX
    Explanations

    locations: anywhere, nowhere, only

    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
    pip
    -0.07
    gh
    -0.06
    ERO
    -0.06
    ök
    -0.06
    ubby
    -0.06
     opa
    -0.06
     Nog
    -0.06
    lish
    -0.06
    æĪijåĽ½çļĦ
    -0.06
    å®ŀçī©
    -0.05
    POSITIVE LOGITS
    使å®ĥ
    0.05
    ×Ļ×ĵ
    0.05
    æĿĪ
    0.05
    使ä¹ĭ
    0.05
    icolon
    0.05
    使åħ¶
    0.05
     empl
    0.05
    еÑĢед
    0.05
    åħ¨éķĩ
    0.05
     supposed
    0.05
    Activations Density 0.026%

    No Known Activations