© 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. 18110
    Prev
    Next
    INDEX
    Explanations

    after use or completion

    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
    åĿĬ
    -0.06
    orks
    -0.06
    ***
    -0.05
    lit
    -0.05
    ston
    -0.05
    arie
    -0.05
    wit
    -0.05
     ÙĤÙĬد
    -0.05
    lic
    -0.05
    stro
    -0.05
    POSITIVE LOGITS
    èħ¥åij³
    0.06
    ä¸įäºĪæĶ¯æĮģ
    0.06
    emony
    0.06
    污æŁĵçݯå¢ĥ
    0.06
    æ°Ĺãģ«åħ¥ãĤĬãģ®
    0.06
    ..\
    0.06
    å±¥è¡ĮåIJĪåIJĮ
    0.06
    ocos
    0.06
    梦éĩĮ
    0.05
    èĻļèį£
    0.05
    Activations Density 0.022%

    No Known Activations