© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22496
    Prev
    Next
    INDEX
    Explanations

    resource depletion

    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
    Negative Logits
    airo
    -0.07
    ellig
    -0.06
    éļıçĿĢæŶéĹ´çļĦæݨ移
    -0.06
    大åĮº
    -0.06
    roupon
    -0.06
    å½Ĵå±ŀäºİä¸Ĭå¸Ĥåħ¬åı¸
    -0.06
    emps
    -0.06
    ksam
    -0.06
    жди
    -0.06
    dong
    -0.06
    POSITIVE LOGITS
    æĪª
    0.06
    éĢĢ
    0.06
    iaz
    0.05
    -
    0.05
    endÅij
    0.05
    解
    0.05
    çĬ
    0.05
    F
    0.05
    çŃ
    0.05
    åīį
    0.05
    Activations Density 0.001%

    No Known Activations