© 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. 19769
    Prev
    Next
    INDEX
    Explanations

    money and sacrifice

    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
    avers
    -0.06
    åħ¶ä»ĸåĽ½å®¶
    -0.06
    aver
    -0.06
    缨
    -0.06
    adora
    -0.05
    ä¸ĭä¸Ģ页
    -0.05
    æIJº
    -0.05
    -sl
    -0.05
    çľĭå¾ħ
    -0.05
    aves
    -0.05
    POSITIVE LOGITS
    anky
    0.05
    phu
    0.05
    thr
    0.05
    üks
    0.05
    é¢Ĩ
    0.05
    ölf
    0.05
     obro
    0.05
    éĹŃéŨ
    0.05
    gel
    0.05
     adel
    0.05
    Activations Density 0.001%

    No Known Activations