© 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. 16941
    Prev
    Next
    INDEX
    Explanations

    pull-ups, rings, exemplary, this

    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
    ç¥Ł
    -0.06
     å¼ķçĶ¨
    -0.06
    atria
    -0.06
    çĥ
    -0.05
    æĶ¾ç®¡
    -0.05
    æľī家
    -0.05
     Ñģкла
    -0.05
     Earn
    -0.05
    hed
    -0.05
    åħ³æİī
    -0.05
    POSITIVE LOGITS
    ä¸Ĭåİ»
    0.06
    riel
    0.06
    ç½ķ
    0.06
    asc
    0.05
     tang
    0.05
     herunter
    0.05
    身é«ĺ
    0.05
    aros
    0.05
    arien
    0.05
     circumcision
    0.05
    Activations Density 0.002%

    No Known Activations