© 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. 17357
    Prev
    Next
    INDEX
    Explanations

    authors of creative works

    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
    onta
    -0.06
    为天
    -0.06
    еÑģа
    -0.06
     Rosenstein
    -0.06
    omit
    -0.06
    ãĤ¹ãĥĪãĥ¼ãĥ«
    -0.06
    ÑħодÑĥ
    -0.06
     Blasio
    -0.06
    ÑĢÑıд
    -0.06
    çļĦç½ijåıĭ
    -0.06
    POSITIVE LOGITS
    zeh
    0.05
     perceived
    0.05
    èĻ¹
    0.05
    çłį
    0.05
    æĭ©
    0.04
     humor
    0.04
    alo
    0.04
    ×Ĺ×ķ
    0.04
    cken
    0.04
    åĩ½
    0.04
    Activations Density 0.020%

    No Known Activations