© 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. 22227
    Prev
    Next
    INDEX
    Explanations

    also known as

    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
    ffect
    -0.06
     ná
    -0.05
    ç±»
    -0.05
    ç±»æݨ
    -0.05
    variably
    -0.05
    ç³»åĪĹ
    -0.05
    åıĬå®īåħ¨
    -0.05
    æİīçļĦ
    -0.05
    AMA
    -0.05
     nis
    -0.05
    POSITIVE LOGITS
    zin
    0.06
    egot
    0.06
    годи
    0.06
    缴è§ĤçļĦæĸ¹å¼ı
    0.06
    hq
    0.06
    ánh
    0.06
    lut
    0.06
    reu
    0.05
    象
    0.05
    ائÙĨ
    0.05
    Activations Density 0.008%

    No Known Activations