© 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. 18401
    Prev
    Next
    INDEX
    Explanations

    broken, cracked, shattered

    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
    åıĬåĪ©æģ¯
    -0.06
     grub
    -0.05
     sleeping
    -0.05
     обеÑīа
    -0.05
     дл
    -0.05
    ç³ľ
    -0.05
    ä¼ijçľł
    -0.05
    éĹªéĹª
    -0.05
    çģ«çĥŃ
    -0.05
    æĮª
    -0.05
    POSITIVE LOGITS
    ç¢İè£Ĥ
    0.09
    çł´ç¢İ
    0.08
     shards
    0.07
    ç¢İçīĩ
    0.07
     fragments
    0.07
    çł´è£Ĥ
    0.07
    frag
    0.07
     Frag
    0.06
    flies
    0.06
     intim
    0.06
    Activations Density 0.034%

    No Known Activations