© 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. 17036
    Prev
    Next
    INDEX
    Explanations

    variable names starting with m_ or self

    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
    å°ģ
    -0.06
    ãĤ³ãĥ¬
    -0.06
    ä½ľåģĩ
    -0.06
    intl
    -0.06
    åĴĮé»Ħ
    -0.06
     gäller
    -0.06
     noop
    -0.06
    éĢ¾æľŁè¿ĺ款
    -0.06
    ä¸İ伦
    -0.05
    неÑĨ
    -0.05
    POSITIVE LOGITS
    اÙĦات
    0.05
     планÑĭ
    0.05
    åĵ¨
    0.05
     Schal
    0.05
    numer
    0.05
    天
    0.05
    ¯
    0.05
     afterward
    0.04
    enable
    0.04
    roe
    0.04
    Activations Density 0.015%

    No Known Activations