© 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. 17997
    Prev
    Next
    INDEX
    Explanations

    degrees Celsius

    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
    trin
    -0.07
    icorn
    -0.07
    åĪ©çī©
    -0.06
    atel
    -0.06
    althy
    -0.06
     Latinoamérica
    -0.06
    pto
    -0.06
     пÑĢоÑħла
    -0.06
    olica
    -0.06
    äste
    -0.06
    POSITIVE LOGITS
    çªģçĦ¶åıijçİ°
    0.06
     exactly
    0.05
    ê°ij
    0.05
    игÑĢÑĭ
    0.05
     striving
    0.05
    udi
    0.05
    äºĮ
    0.04
    dire
    0.04
     trying
    0.04
    æī¾åĪ°ä¸Ģ个
    0.04
    Activations Density 0.052%

    No Known Activations