© 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. 18731
    Prev
    Next
    INDEX
    Explanations

    dependence

    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
     congr
    -0.05
    oby
    -0.05
    transparent
    -0.05
     transmettre
    -0.05
     hon
    -0.05
     metu
    -0.05
    æŶåĢĻ
    -0.05
     transparent
    -0.05
    å¿ĥ声
    -0.05
    bih
    -0.05
    POSITIVE LOGITS
    èĪĪ奮
    0.06
    edi
    0.06
    è¦ģæ±Ĥ被åijĬ
    0.06
    airo
    0.06
     degr
    0.06
    èĪ±
    0.05
    å¼ķ
    0.05
    æĴ¤
    0.05
    çŃīç³»åĪĹ
    0.05
     rafra
    0.05
    Activations Density 0.014%

    No Known Activations