© 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. 16996
    Prev
    Next
    INDEX
    Explanations

    control, possession, capture, seizing

    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
     accom
    -0.06
    åħµåĽ¢
    -0.05
    æ³ķå¼ı
    -0.05
     measurable
    -0.05
    Ã¶ÃŁer
    -0.05
     (“
    -0.05
    elman
    -0.05
     nhắm
    -0.05
    å°º
    -0.05
    å¹ħ度
    -0.05
    POSITIVE LOGITS
    upe
    0.06
    agé
    0.06
    ä¼łéĢĴ
    0.06
    åĴĮä½ľçĶ¨
    0.06
    nip
    0.06
    agée
    0.06
    angg
    0.06
    ãģ«éĢļ
    0.06
    æī¼
    0.06
    åĪ©å¼Ĭ
    0.06
    Activations Density 0.005%

    No Known Activations