© 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. 21308
    Prev
    Next
    INDEX
    Explanations

    border properties

    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
    Magn
    -0.06
    æĮĩ示
    -0.06
    大å¹ħ度
    -0.06
    æĭ¿åĩº
    -0.05
     choc
    -0.05
     Magn
    -0.05
    è¿ĻäºĽéĥ½
    -0.05
    holders
    -0.05
    agnostic
    -0.05
    åĺ
    -0.05
    POSITIVE LOGITS
    nection
    0.07
    å¹³éĺ³
    0.06
    autant
    0.06
     tránsito
    0.06
    ä¸Ģåı¶
    0.06
    acol
    0.06
    åĬłæĭ¿å¤§çļĦ
    0.06
    使çĶ¨æĥħåĨµ
    0.06
    zis
    0.06
     concurrent
    0.06
    Activations Density 0.007%

    No Known Activations