© 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. 20132
    Prev
    Next
    INDEX
    Explanations

    including a variety of

    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
    пÑĢоÑĩем
    -0.06
    icine
    -0.06
    asu
    -0.06
    apur
    -0.06
    pires
    -0.06
     Horny
    -0.06
    éĶ¦æ¶Ľ
    -0.06
    å°ıå¹ħ
    -0.06
    ä»¥ä¹łè¿ijå¹³
    -0.06
    venes
    -0.06
    POSITIVE LOGITS
    家家
    0.05
     Thanks
    0.05
     these
    0.05
     hele
    0.05
     cele
    0.05
     thanks
    0.05
    éĻĪ
    0.05
    b
    0.04
     therein
    0.04
     whole
    0.04
    Activations Density 0.024%

    No Known Activations