© 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. 20065
    Prev
    Next
    INDEX
    Explanations

    about you / gay

    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
    uya
    -0.06
    åİī害äºĨ
    -0.06
     relaxing
    -0.06
    hea
    -0.06
    erek
    -0.06
    çŁŃ
    -0.06
     Relax
    -0.05
    ÃŃta
    -0.05
    åĭĥèµ·
    -0.05
    æĵ
    -0.05
    POSITIVE LOGITS
    èĢĮéĿŀ
    0.07
    èĢĮä¸įæĺ¯
    0.07
     rather
    0.06
    unn
    0.06
     sens
    0.06
    poss
    0.06
    alar
    0.06
    سÙĨ
    0.05
    rather
    0.05
     hanem
    0.05
    Activations Density 0.147%

    No Known Activations