© 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. 20245
    Prev
    Next
    INDEX
    Explanations

    appellantSenatorKingdefendant

    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
    为äºĨéĺ²æŃ¢
    -0.07
    ÑģÑĤÑĢи
    -0.06
    ature
    -0.06
    åıĸç·ł
    -0.06
    为äºĨç¡®ä¿Ŀ
    -0.06
    为äºĨéģ¿åħį
    -0.05
    ç³ľçĥĤ
    -0.05
    为äºĨæĸ¹ä¾¿
    -0.05
    éric
    -0.05
    为äºĨæıIJé«ĺ
    -0.05
    POSITIVE LOGITS
    çħ§
    0.06
     pare
    0.06
    ithe
    0.05
    енÑĤаÑĨиÑı
    0.05
    pell
    0.05
    ssp
    0.05
    åħīçħ§
    0.05
    zp
    0.05
    구
    0.05
     Roh
    0.05
    Activations Density 0.005%

    No Known Activations