© 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. 21599
    Prev
    Next
    INDEX
    Explanations

    cause/lead to

    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
     furthermore
    -0.05
    nbsp
    -0.05
     consequently
    -0.05
    éĿĻçļĦ
    -0.05
     -
    -0.05
    bilt
    -0.05
    æĺŁçļĦ
    -0.05
    çĶ²çŃī
    -0.05
    çĦ¶
    -0.05
    å·
    -0.05
    POSITIVE LOGITS
    zicht
    0.07
    ulte
    0.06
    ÑĢÑĭз
    0.06
    ultos
    0.06
    DefaultValue
    0.06
    æĹłéĩı
    0.06
     demais
    0.06
    èĻķæĸ¼
    0.06
    æ»Ķ
    0.06
    ãĥĨãĤ£
    0.06
    Activations Density 0.228%

    No Known Activations