© 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. 17246
    Prev
    Next
    INDEX
    Explanations

    survival horror

    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
    pal
    -0.05
    воÑĹ
    -0.05
    é«ĺè¶ħ
    -0.05
    å·²ç»ıè¶ħè¿ĩ
    -0.05
    opal
    -0.05
    جر
    -0.05
    å·®ãģĹ
    -0.05
    ë¡ľëıĦ
    -0.05
     sto
    -0.05
    è§ĦèĮĥ
    -0.04
    POSITIVE LOGITS
    çĶŁåŃĺ
    0.07
     survival
    0.06
     shrinking
    0.06
     survivor
    0.06
    çĶŁåŃĺçļĦ
    0.06
     pare
    0.06
    ä¸įåĪ©
    0.06
    çĻ¾å·Ŀ
    0.06
    缩çŁŃ
    0.06
    åİ®æĿĢ
    0.06
    Activations Density 0.006%

    No Known Activations