© 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. 19323
    Prev
    Next
    INDEX
    Explanations

    space, stars, solar system, moon

    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
    opan
    -0.06
    äºĭæĥħ
    -0.05
     Formation
    -0.05
     circumcision
    -0.05
     Huy
    -0.05
    Ïĥια
    -0.05
    ammans
    -0.05
    å½¢æĪIJçļĦ
    -0.05
    沧æ¡ij
    -0.05
     Libre
    -0.05
    POSITIVE LOGITS
    åı©
    0.06
    çļĦ羣
    0.06
    vent
    0.06
    çĻ½äºĨ
    0.06
    oria
    0.06
     Ree
    0.06
    çģ¼
    0.06
    æģ¯
    0.06
    VENT
    0.05
    被å°ģ
    0.05
    Activations Density 0.006%

    No Known Activations