© 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. 18931
    Prev
    Next
    INDEX
    Explanations

    observable things

    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
    udara
    -0.07
    å¾ĢæľŁç²¾å½©
    -0.07
    elaar
    -0.06
    hsi
    -0.06
    ENTIC
    -0.06
    ton
    -0.06
    atism
    -0.06
    ê°Ģì§Ģ
    -0.06
    mlin
    -0.06
    çħ¤çģ°
    -0.06
    POSITIVE LOGITS
    å¤ĸçļĦ
    0.08
    ез
    0.06
     اÙĦÙħب
    0.06
    ей
    0.05
    c
    0.05
    ãģĦãģª
    0.05
    oy
    0.05
    аÑĤÑĮ
    0.05
    åħ¶äºĭ
    0.05
    inizi
    0.05
    Activations Density 0.007%

    No Known Activations