© 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. 18834
    Prev
    Next
    INDEX
    Explanations

    writing and orthography

    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
    èĵ
    -0.06
    òng
    -0.06
    é¦
    -0.05
     Pierce
    -0.05
    æŃ¹
    -0.05
    /licenses
    -0.05
    èį
    -0.05
    ä»ĭ
    -0.05
    åħ¸åŀĭçļĦ
    -0.05
    ilangan
    -0.05
    POSITIVE LOGITS
    äºī缸
    0.06
    äºīè®®çļĦ
    0.06
    è§ĦèĮĥçļĦ
    0.06
    çºłç»ĵ
    0.06
    ä¹ĭäºī
    0.06
     puntu
    0.06
     concernés
    0.06
    lord
    0.05
     egreg
    0.05
    äºī论
    0.05
    Activations Density 0.049%

    No Known Activations