© 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. 16839
    Prev
    Next
    INDEX
    Explanations

    links to further information

    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
     sufficiently
    -0.06
    -stream
    -0.05
    çī¹
    -0.05
     dominant
    -0.05
     its
    -0.05
    èĪ
    -0.05
    ä¸Ĭè¿°äºĭå®ŀ
    -0.05
     process
    -0.05
     primarily
    -0.05
    类似çļĦ
    -0.05
    POSITIVE LOGITS
    quen
    0.06
     veille
    0.06
    evo
    0.06
    øv
    0.06
    ijs
    0.06
    è°ģ家
    0.06
    ushed
    0.05
    amme
    0.05
    iems
    0.05
    verige
    0.05
    Activations Density 0.030%

    No Known Activations