© 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. 18400
    Prev
    Next
    INDEX
    Explanations

    referring to people

    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
    æѤ
    -0.06
    åħ¶
    -0.06
    å®ĥ
    -0.06
    æľºéģĩ
    -0.06
    ify
    -0.05
    ipse
    -0.05
    inder
    -0.05
    ipt
    -0.05
    리
    -0.05
    irage
    -0.05
    POSITIVE LOGITS
    说æĪij
    0.07
    çĿĢ她çļĦ
    0.06
    被ä»ĸ
    0.06
    çĿĢæĪij们çļĦ
    0.06
    çī¹å¾ģæĺ¯
    0.06
    çŃīæĪij
    0.06
    æľīåħ³æ³ķå¾ĭ
    0.06
    çĿĢæĪijçļĦ
    0.06
    被她
    0.06
    åģ¥åº·å®īåħ¨
    0.06
    Activations Density 0.018%

    No Known Activations