© 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. 20304
    Prev
    Next
    INDEX
    Explanations

    habitation on other planets

    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
    ogne
    -0.06
    è¹Ħ
    -0.06
    opian
    -0.05
    éĥİ
    -0.05
    راج
    -0.05
    妨
    -0.05
     Afg
    -0.05
    çī§
    -0.05
     finder
    -0.05
    åħ¬è¯īæľºåħ³
    -0.05
    POSITIVE LOGITS
    åħ¨å¥Ĺ
    0.06
     vit
    0.05
     Lemb
    0.05
     conç
    0.05
    èĪ¶
    0.05
    纬
    0.05
    lander
    0.05
     aboard
    0.05
     Martian
    0.05
    .Slice
    0.05
    Activations Density 0.012%

    No Known Activations